Pasar al contenido principal

COMPRENSION DEL LENGUAJE EN LOS MEDIOS DE COMUNICACION SOCIAL - REPRESENTANDO CONTEXTOS DE FORMA CONTINUA

TIN2015-71147-C2-1-P

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D (Excelencia / Generación de Conocimiento)
Año convocatoria 2015
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Secretaría de Estado de Educación, Formación Profesional y Universidades
Centro beneficiario UNIVERSITAT POLITÈCNICA DE VALÈNCIA
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 32
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Tesis doctoral (DoctoralThesis)

Sarcasm and Implicitness in Abusive Language Detection: A Multilingual Perspective

  • Frenda, Simona
[ES] La posibilidad de monitorear el contenido de odio en línea a partir de lo que escribe la gente se está convirtiendo en un asunto muy importante para varios actores, como gobiernos, empresas de TIC y profesionales de ONG's que implementan campañas de sensibilización en respuesta al preocupante aumento de los abusos y de la incitación al odio en línea. El abusive language es un término genérico que se utiliza para definir los contenidos hostiles generados por usuarios, que intimidan o incitan a la violencia y al desprecio, dirigiéndose a grupos vulnerables en las redes sociales. Hoy en día, estos contenidos están muy extendidos, y se encuentran también en otros tipos de textos como los artículos y títulos de periódicos online. Se han implementado varios enfoques en los últimos años para apoyar la identificación y el monitoreo de estos fenómenos, lamentablemente estos están lejos de resolver el problema debido a la complejidad interna del lenguaje abusivo y las dificultades para detectar sus formas más implícitas. En nuestra investigación de doctorado, hemos examinado las cuestiones relacionadas con la identificación automática del lenguaje abusivo en línea, investigando las diferentes maneras de hostilidad contra las mujeres, los inmigrantes y las comunidades culturales minoritarias, en idiomas como el italiano, el inglés y el español. El marco multilingüe nos ha permitido tener un enfoque comparativo para reflexionar sobre cómo se expresa el discurso de odio en varios idiomas, y cómo dichas expresiones se deben representar en el proceso automático del texto. El análisis de los resultados de los distintos métodos de clasificación de los mensajes en relación con la presencia del lenguaje abusivo, ha sacado a la luz algunas dificultades principalmente vinculadas a sus manifestaciones más implícitas. Por ejemplo, en los casos en que se utilizan figuras retóricas (como la ironía y el sarcasmo), cuando se fortalecen ideologías (como la ideología sexista) o esquemas cognitivos (como los estereotipos), o cuando se postulan contrarias a un tema de discusión. Para abordar estas dificultades, hemos propuesto distintas soluciones que también se pueden aplicar a diferentes géneros textuales. En particular, hemos observado que los aspectos cognitivos y creativos del discurso del odio son más difíciles de deducir automáticamente de los textos. Al mismo tiempo, también son elementos muy recurrentes como el caso del sarcasmo un recurso retórico que tiende a socavar la precisión de los sistemas. De hecho, por sus peculiaridades, el sarcasmo es adecuado para enmascarar mensajes ofensivos, especialmente en textos muy breves e informales. Nuestra hipótesis es que al informar al sistema sobre la presencia del sarcasmo, se mejoraría la identificación de los mensajes de odio, incluso cuando estos están disfrazados de sarcásticos. Para ello, es interesante estudiar cómo la introducción de conocimientos lingüísticos en modelos de detección puede ser útil para capturar los niveles de significado más implícitos. En concreto, hemos creado nuevos recursos que nos permitieron profundizar en nuestra hipótesis y desarrollar diversos enfoques para identificar dos maneras de lenguaje abusivo en tuits y títulos de periódicos: los discursos de odio y los estereotipos. Nuestra idea es combinar de manera fructífera el conocimiento general de los modelos lingüísticos y la información lingüística obtenida mediante la extracción de elementos lingüísticos específicos o entrenando simultáneamente el sistema al reconocimiento del lenguaje irónico en una arquitectura multitarea. Los resultados experimentales confirman que hacer que los sistemas sean conscientes del sarcasmo mejora el reconocimiento del discurso de odio y los estereotipos en los textos de las redes sociales, como los tuits. Al informarles de elementos lingüísticos específicos, se vuelven más sensibles a la identificación de estereotipos tanto en los tuits como en los títulos de periódicos., [CA] La possibilitat de monitorar el contingut d'odi en línia a partir del que escriu la gent s'està convertint en un assumpte molt important per a diversos actors, com ara governs, empreses de TIC i professionals d'ONGs que implementen campanyes de sensibilització en resposta al preocupant augment dels abusos i de la incitació a l'odi en línia. L'abusive language és un terme genèric que s'utilitza per definir els continguts hostils generats per usuaris, que intimiden o inciten a la violència i al menyspreu, adreçant-se a grups vulnerables a les xarxes socials. Avui dia, aquests continguts estan molt estesos, i es troben també en altres tipus de textos com els articles i títols de diaris en línia. S'han implementat diversos enfocaments en els darrers anys per donar suport a la identificació i monitoratge d'aquests fenòmens, lamentablement aquests estan lluny de resoldre el problema a causa de la complexitat interna del llenguatge abusiu i les dificultats per detectar-ne les formes més implícites. A la nostra investigació de doctorat, hem examinat les qüestions relacionades amb la identificació automàtica del llenguatge abusiu en línia, investigant les diferents maneres d'hostilitat contra les dones, els immigrants i les comunitats culturals minoritàries, en idiomes com l'italià, l'anglès i l'espanyol. El marc multilingüe ens ha permès tenir un enfocament comparatiu per reflexionar sobre com s'expressa el discurs d'odi en diversos idiomes, i com s'han de representar aquestes expressions en el procés automàtic del text. L'anàlisi dels resultats dels diferents mètodes de classificació dels missatges en relació amb la presència del llenguatge abusiu ha tret a la llum algunes dificultats principalment vinculades a les manifestacions més implícites. Per exemple, en els casos en què es fan servir figures retòriques (com la ironia i el sarcasme), quan s'enforteixen ideologies (com la ideologia sexista) o esquemes cognitius (com els estereotips), o quan es postulen contràries a un tema de discussió. Per abordar aquestes dificultats, hem proposat diferents solucions que també es poden aplicar a diferents gèneres textuals. En particular, hem observat que els aspectes cognitius i creatius del discurs de l'odi són més difícils de deduir automàticament dels textos. Alhora, també són elements molt recurrents com el cas del sarcasme un recurs retòric que tendeix a soscavar la precisió dels sistemes. De fet, per les seves peculiaritats, el sarcasme és adequat per emmascarar missatges ofensius, especialment en textos molt breus i informals com els publicats a Twitter. La nostra hipòtesi és que en informar el sistema sobre la presència del sarcasme, es milloraria la identificació dels missatges d'odi, fins i tot quan aquests estan disfressats de sarcàstics. Per això, és interessant estudiar com la introducció de coneixements lingüístics en models de detecció pot ser útil per capturar els nivells de significat més implícits. En concret, hem creat nous recursos que ens han permès aprofundir en la nostra hipòtesi i desenvolupar diversos enfocaments per identificar dues maneres de llenguatge abusiu en tuits i títols de diaris: el discurs d'odi (o hate speech) i els estereotips. La nostra idea és combinar de manera fructífera el coneixement general dels models lingüístics i la informació lingüística obtinguda mitjançant l'extracció d'elements lingüístics específics o entrenant simultàniament el sistema al reconeixement del llenguatge irònic en una arquitectura multitasca. Els resultats experimentals confirmen que fer que els sistemes siguin conscients del sarcasme millora el reconeixement del discurs d'odi i els estereotips als textos de les xarxes socials, com els tuits. En informar-los d'elements lingüístics específics, esdevenen més sensibles a la identificació d'estereotips tant als tuits com als títols de diaris., [EN] The possibility to monitor hateful content online on the basis of what people write is becoming an important topic for several actors such as governments, ICT companies, and NGO's operators conducting active campaigns in response to the worrying rise of online abuse and hate speech. Abusive language is a broad umbrella term which is commonly used for denoting different kinds of hostile user-generated contents that intimidate or incite to violence and hatred, targeting many vulnerable groups in social platforms. Such hateful contents are pervasive nowadays and can also be detected even in other kinds of texts, such as online newspapers. Various approaches have been proposed in the last years to support the identification and monitoring of these phenomena, but unfortunately, they are far from solving the problem due to the inner complexity of abusive language, and to the difficulties to detect its implicit forms. In our doctoral investigation, we have studied the issues related to automatic identification of abusive language online, investigating various forms of hostility against women, immigrants and cultural minority communities in languages such as Italian, English, and Spanish. The multilingual frame allowed us to have a comparative setting to reflect on how hateful contents are expressed in distinct languages and how these different ways are transposed in the automated processing of the text. The analysis of the results of different methods of classification of hateful and non-hateful messages revealed important challenges that lie principally on the implicitness of some manifestations of abusive language expressed through the use of figurative devices (i.e., irony and sarcasm), recall of inner ideologies (i.e., sexist ideology) or cognitive schemas (i.e., stereotypes), and expression of unfavorable stance. To face these challenges, in this work, we have proposed distinct solutions applicable also to different textual genres. We observed that, in particular, cognitive and creative aspects of abusive language are harder to infer automatically from texts. At the same time they are often recurrent elements, such in the case of sarcasm, a figurative device that tends to affect the accuracy of the systems. Indeed, for its peculiarities, sarcasm is apt to disguise hurtful messages, especially in short and informal texts such as the ones posted on Twitter. Our hypothesis is that information about the presence of sarcasm could help to improve the detection of hateful messages, even when they are camouflaged as sarcastic. In this perspective, it is interesting to study how the injection of linguistic knowledge into detection models can be useful to capture implicit levels of meaning. In particular, we created novel resources that allowed us to examine deeply our hypothesis and develop specific approaches for the detection of two forms of abusive language in tweets and headlines: hate speech and stereotypes. Our idea was to fruitfully combine general knowledge from language models and linguistic information, obtained with specific linguistic features and the injection of ironic language recognition within a multi-task learning framework. The experimental results confirm that the awareness of sarcasm helps systems to retrieve correctly hate speech and stereotypes in social media texts, such as tweets. Moreover, linguistic features make the system sensible to stereotypes in both tweets and news headlines., This work was partially supported by various financial projects. Among them: the Spanish research project SomEMBED funded by Ministerio de Economía y Sostenibilidad (MINECO), the NII International Internship Program funded by JSPS KAKENHI, the Italian project M.EMO.RAI funded by RAI - Radiotelevisione Italiana Spa, the Italian project IhatePrejudice funded by Compagnia di San Paolo, and the European project “STERHEOTYPES” funded by Compagnia di San Paolo Foundation, Volkswagen Stiftung and Carlsberg Fondation.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

On the Use of Character n-grams as the only Intrinsic Evidence of Plagiarism

  • Bensalem, Imene
  • Chikhi, Salim
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] When a shift in writing style is noticed in a document, doubts arise about its originality. Based on this clue to plagiarism, the intrinsic approach to plagiarism detection identifies the stolen passages by analysing the writing style of the suspicious document without comparing it to textual resources that may serve as sources for the plagiarist. Character n-grams are recognised as a successful approach to modelling text for writing style analysis. Although prior studies have investigated the best practice of using character n-grams in authorship attribution and other problems, there is still a need for such investigations in the context of intrinsic plagiarism detection. Moreover, it has been assumed in previous works that the ways of using character n-grams in authorship attribution remain the same for intrinsic plagiarism detection. In this paper, we study the effect of character n-grams frequency and length on the performance of intrinsic plagiarism detection. Our experiments utilise two state-of-the-art methods and five large document collections of PAN labs written in English and Arabic. We demonstrate empirically that the low- and the high-frequency n-grams are not equally relevant for intrinsic plagiarism detection, but their performance depends on the way they are exploited., We are very grateful to the anonymous reviewers for their insightful suggestions and constructive comments that greatly improved the paper. This work has been partially supported by the Ecole Superieure de Comptabilite et de Finances de Constantine. The work of Paolo Rosso has been partially funded by the SomEMBED TIN2015-71147-C2-1-P research project (MINECO/FEDER). The work of Salim Chikhi has been partially funded by CNEPRU/DGRSDT/B*07120140018 research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A resource-light method for cross-lingual semantic textual similarity

  • Glavas, Goran
  • Franco-Salvador, Marc
  • Ponzetto, Simone Paolo
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Recognizing semantically similar sentences or paragraphs across languages is beneficial for many tasks, ranging from cross-lingual information retrieval and plagiarism detection to machine translation. Recently proposed methods for predicting cross-lingual semantic similarity of short texts, however, make use of tools and resources (e.g., machine translation systems, syntactic parsers or named entity recognition) that for many languages (or language pairs) do not exist. In contrast, we propose an unsupervised and a very resource-light approach for measuring semantic similarity between texts in different languages. To operate in the bilingual (or multilingual) space, we project continuous word vectors (i.e., word embeddings) from one language to the vector space of the other language via the linear translation model. We then align words according to the similarity of their vectors in the bilingual embedding space and investigate different unsupervised measures of semantic similarity exploiting bilingual embeddings and word alignments. Requiring only a limited-size set of word translation pairs between the languages, the proposed approach is applicable to virtually any pair of languages for which there exists a sufficiently large corpus, required to learn monolingual word embeddings. Experimental results on three different datasets for measuring semantic textual similarity show that our simple resource-light approach reaches performance close to that of supervised and resource-intensive methods, displaying stability across different language pairs. Furthermore, we evaluate the proposed method on two extrinsic tasks, namely extraction of parallel sentences from comparable corpora and cross-lingual plagiarism detection, and show that it yields performance comparable to those of complex resource-intensive state-of-the-art models for the respective tasks. (C) 2017 Published by Elsevier B.V., Part of the work presented in this article was performed during second author's research visit to the University of Mannheim, supported by Contact Fellowship awarded by the DAAD scholarship program "STIBET Doktoranden". The research of the last author has been carried out in the framework of the SomEMBED project (TIN2015-71147-C2-1-P). Furthermore, this work was partially funded by the Junior-professor funding programme of the Ministry of Science, Research and the Arts of the state of Baden-Wurttemberg (project "Deep semantic models for high-end NLP application").
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Affect and Interaction in Agent-Based Systems and Social Media: Guest Editors Introduction

  • Clavel, Chloe
  • Damiano, Rossana
  • Patti, Viviana
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Today¿s Internet is evolving toward an open society of humans and computational entities, where intelligent agent systems increasingly support the interaction between users and computational components. In this scenario, affect plays a key role, with functions that span from creating and maintaining interpersonal relations, to establishing cooperation and trust. Artificial systems¿which can act as both actors and facilitators of these interactions¿are more and more requested to integrate affective components in order to achieve truly realistic social behaviors and foster the creation of bonds with the users, with timely reactions to their affective input and appropriate expressions of affect. Achieving this integration requires to understand and reproduce the role of affect in human expressive capabilities, and to account for affect-related phenomena (e.g., sentiment, emotions, and mood) that engage social abilities, such as empathy, and expressive means, such as irony. The expectation for complex phenomena such as empathy and irony is that effective approaches require an interdisciplinary approach and, above all, the integration of representational models and data-oriented processing techniques. The aim of this special section is to bring together leading research on computational models of affect-related phenomena in interactions occurring either in social media or agent-based systems, by attaining cross-fertilization between two relevant perspectives: on the one hand, research on agent architectures and cognitive models, mainly concerned with the integration of affective states into agents and open to the creation of virtual and embodied agents; on the other hand, research on techniques for sentiment analysis and opinion mining, mainly focused on the processing of affective information in social media, typically (but not only) expressed through text. The integration of models and methods between the two perspectives can open the way to the development of a new generation of social and interactive applications that leverage the affective dimension to promote improved, spontaneous technologymediated interactions, including human¿computer and human¿human interactions, on small and large scale. Our goal here is to provide an overview of the open research challenges for the community of researchers interested in analyzing and modeling the interplay between affect and interaction in agent-based systems and social media, as well as an introduction to the special section. The rest of the article is structured as follows. Section 2 discusses a set of research challenges relevant in the context of this special issue, Section 3 briefly introduces the articles included in this ACM TOIT special section. Section 4 concludes the article., The work of Viviana Patti was partially carried out at the Universitat Politecnica de Valencia within the framework of a fellowship of the University of Turin co-funded by Fondazione CRT (World Wide Style Program 2). The work of Paolo Rosso has been partially funded by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the grant ALMAMATER (PrometeoII/2014/030).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Continuous Space Models for CLIR

  • Gupta, Parth
  • Banchs, Rafael
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] We present and evaluate a novel technique for learning cross-lingual continuous space models to aid cross-language information retrieval (CLIR). Our model, which is referred to as external-data composition neural network (XCNN), is based on a composition function that is implemented on top of a deep neural network that provides a distributed learning framework. Different from most existing models, which rely only on available parallel data for training, our learning framework provides a natural way to exploit monolingual data and its associated relevance metadata for learning continuous space representations of language. Cross-language extensions of the obtained models can then be trained by using a small set of parallel data. This property is very helpful for resource-poor languages, therefore, we carry out experiments on the English-Hindi language pair. On the conducted comparative evaluation, the proposed model is shown to outperform state-of-the-art continuous space models with statistically significant margin on two different tasks: parallel sentence retrieval and ad-hoc retrieval., We thank German Sanchis Trilles for helping in conducting experiments with machine translation. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GeForce Titan GPU used for this research. The research of the first author was supported by FPI grant of UPV. The research of the third author is supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the grant ALMAMATER (PrometeolI/2014/030).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Semantically-informed distance and similarity measures for paraphrase plagiarism identification

  • Álvarez Carmona, M.A.
  • Franco-Salvador, Marc
  • Villatoro-Tello, Esaú
  • Montes Gomez, Manuel
  • Villaseñor Pineda, Luis
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques. Accordingly, this paper introduces two new measures for evaluating the relatedness of two given texts: a semantically-informed similarity measure and a semantically-informed edit distance. Both measures are able to extract semantic information from either an external resource or a distributed representation of words, resulting in informative features for training a supervised classifier for detecting paraphrase plagiarism. Obtained results indicate that the proposed metrics are consistently good in detecting different types of paraphrase plagiarism. In addition, results are very competitive against state-of-the art methods having the advantage of representing a much more simple but equally effective solution., This work was partially supported by CONACYT under scholarship 401887, project grants 257383, 258588 and 2016-01-2410 and under the Thematic Networks program (Language Technologies Thematic Network project 281795). The work of the fourth author was partially supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the grant ALMAMATER (Prometeo II/2014/030).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Character N-Grams for Detecting Deceptive Controversial Opinions

  • Sánchez-Junquera, Juan Javier
  • Luis Villaseñor Pineda
  • Montes Gomez, Manuel
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Controversial topics are present in the everyday life, and opinions about them can be either truthful or deceptive. Deceptive opinions are emitted to mislead other people in order to gain some advantage. In the most of the cases humans cannot detect whether the opinion is deceptive or truthful, however, computational approaches have been used successfully for this purpose. In this work, we evaluate a representation based on character n-grams features for detecting deceptive opinions. We consider opinions on the following: abortion, death penalty and personal feelings about the best friend; three domains studied in the state of the art. We found character n-grams effective for detecting deception in these controversial domains, even more than using psycholinguistic features. Our results indicate that this representation is able to capture relevant information about style and content useful for this task. This fact allows us to conclude that the proposed one is a competitive text representation with a good trade-off between simplicity and performance., We would like to thank CONACyT for partially supporting this work under grants 613411, CB-2015-01-257383, and FC-2016/2410. The work of the last author was partially funded by the Spanish MINECO under the research project SomEMBED (TIN2015-71147-C2-1-P).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

On the use of word embedding for cross language plagiarism detection

  • Asghari, Habibollah
  • Fatemi, Omid
  • Mohtaj, Salar
  • Faili, Heshaam
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Cross language plagiarism is the unacknowledged reuse of text across language pairs. It occurs if a passage of text is translated from source language to target language and no proper citation is provided. Although various methods have been developed for detection of cross language plagiarism, less attention has been paid to measure and compare their performance, especially when tackling with different types of paraphrasing through translation. In this paper, we investigate various approaches to cross language plagiarism detection. Moreover, we present a novel approach to cross language plagiarism detection using word embedding methods and explore its performance against other state-of-the-art plagiarism detection algorithms. In order to evaluate the methods, we have constructed an English-Persian bilingual plagiarism detection corpus (referred to as HAMTA-CL) comprised of seven types of obfuscation. The results show that the word embedding approach outperforms the other approaches with respect to recall when encountering heavily paraphrased passages. On the other hand, translation based approach performs well when the precision is the main consideration of the cross language plagiarism detection system.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Code Mixed Cross Script Factoid Question Classification - A Deep Learning Approach

  • Banerjee, Somnath
  • Kumar Naskar, Sudip
  • Bandyopadhyay, Sivaji
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Before the advent of the Internet era, code-mixing was mainly used in the spoken form. However, with the recent popular informal networking platforms such as Facebook, Twitter, Instagram, etc., in social media, code-mixing is being used more and more in written form. User-generated social media content is becoming an increasingly important resource in applied linguistics. Recent trends in social media usage have led to a proliferation of studies on social media content. Multilingual social media users often write native language content in non-native script (cross-script). Recently Banerjee et al. [9] introduced the code-mixed cross-script question answering research problem and reported that the ever increasing social media content could serve as a potential digital resource for less-computerized languages to build question answering systems. Question classification is a core task in question answering in which questions are assigned a class or a number of classes which denote the expected answer type(s). In this research work, we address the question classification task as part of the code-mixed cross-script question answering research problem. We combine deep learning framework with feature engineering to address the question classification task and enhance the state-of-the-art question classification accuracy by over 4% for code-mixed cross-script questions., The work of the third author was partially supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Fake Opinion Detection: How Similar are Crowdsourced Datasets to Real Data?

  • Fornaciari, Tommaso
  • Cagnina, Leticia
  • Poesio, Massimo
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Identifying deceptive online reviews is a challenging tasks for Natural Language Processing (NLP). Collecting corpora for the task is difficult, because normally it is not possible to know whether reviews are genuine. A common workaround involves collecting (supposedly) truthful reviews online and adding them to a set of deceptive reviews obtained through crowdsourcing services. Models trained this way are generally successful at discriminating between `genuine¿ online reviews and the crowdsourced deceptive reviews. It has been argued that the deceptive reviews obtained via crowdsourcing are very different from real fake reviews, but the claim has never been properly tested. In this paper, we compare (false) crowdsourced reviews with a set of `real¿ fake reviews published on line. We evaluate their degree of similarity and their usefulness in training models for the detection of untrustworthy reviews. We find that the deceptive reviews collected via crowdsourcing are significantly different from the fake reviews published online. In the case of the artificially produced deceptive texts, it turns out that their domain similarity with the targets affects the models¿ performance, much more than their untruthfulness. This suggests that the use of crowdsourced datasets for opinion spam detection may not result in models applicable to the real task of detecting deceptive reviews. As an alternative method to create large-size datasets for the fake reviews detection task, we propose methods based on the probabilistic annotation of unlabeled texts, relying on the use of meta-information generally available on the e-commerce sites. Such methods are independent from the content of the reviews and allow to train reliable models for the detection of fake reviews., Leticia Cagnina thanks CONICET for the continued financial support. This work was funded by MINECO/FEDER (Grant No. SomEMBED TIN2015-71147-C2-1-P). The work of Paolo Rosso was partially funded by the MISMIS-FAKEnHATE Spanish MICINN research project (PGC2018-096212-B-C31). Massimo Poesio was in part supported by the UK Economic and Social Research Council (Grant Number ES/M010236/1).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Multilevel Approach to Sentiment Analysis of Figurative Language in Twitter

  • Gopal Patra, Braja
  • Mazumda, Soumadeep
  • Das, Dipankar
  • Bandyopadhyay, Sivaji
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Commendable amount of work has been attempted in the field of Sentiment Analysis or Opinion Mining from natural language texts and Twitter texts. One of the main goals in such tasks is to assign polarities (positive or negative) to a piece of text. But, at the same time, one of the important as well as difficult issues is how to assign the degree of positivity or negativity to certain texts. The answer becomes more complex when we perform a similar task on figurative language texts collected from Twitter. Figurative language devices such as irony and sarcasm contain an intentional secondary or extended meaning hidden within the expressions. In this paper we present a novel approach to identify the degree of the sentiment (fine grained in an 11-point scale) for the figurative language texts. We used several semantic features such as sentiment and intensifiers as well as we introduced sentiment abruptness, which measures the variation of sentiment from positive to negative or vice versa. We trained our systems at multiple levels to achieve the maximum cosine similarity of 0.823 and minimum mean square error of 2.170., The work reported in this paper is supported by a grant from the project “CLIA System Phase II” funded by Department of Electronics and Information Technology (DeitY), Ministry of Communications and Information Technology (MCIT), Government of India. The work of the fourth author is also supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the grant ALMAPATER (PrometeoII/2014/030).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Figurative Messages and Affect in Twitter: Differences Between #irony, #sarcasm and #not

  • Sulis, Emilio
  • Hernandez-Farias, Delia Irazu
  • Patti, Viviana
  • Ruffo, Giancarlo
  • Rosso, Paolo|||0000-0002-8922-1242
The use of irony and sarcasm has been proven to be a pervasive phenomenon in social media posing a challenge to sentiment analysis systems. Such devices, in fact, can influence and twist the polarity of an utterance in different ways. A new dataset of over 10,000 tweets including a high variety of figurative language types, manually annotated with sentiment scores, has been released in the context of the task 11 of SemEval-2015. In this paper, we propose an analysis of the tweets in the dataset to investigate the open research issue of how separated figurative linguistic phenomena irony and sarcasm are, with a special focus on the role of features related to the multi-faceted affective information expressed in such texts. We considered for our analysis tweets tagged with #irony and #sarcasm, and also the tag #not, which has not been studied in depth before. A distribution and correlation analysis over a set of features, including a wide variety of psycholinguistic and emotional features, suggests arguments for the separation between irony and sarcasm. The outcome is a novel set of sentiment, structural and psycholinguistic features evaluated in binary classification experiments. We report about classification experiments carried out on a previously used corpus for #irony vs #sarcasm. We outperform in terms of F-measure the stateof-the-art results on this dataset. Overall, our results confirm the difficulty of the task, but introduce new data-driven arguments for the separation between #irony and #sarcasm. Interestingly, #not emerges as a distinct phenomenon. © 2016 Elsevier B.V. All rights reserved., The National Council for Science and Technology (CONACyT Mexico) has funded the research work of Delia Irazu Hernandez Farias (Grant No. 218109/313683 CVU-369616). Paolo Rosso has been partially funded by SomEMBED MINECO research project (TIN2015-71147-C2-1-P) and by the Generalitat Valenciana under the grant ALMAMATER (PrometeoII/2014/030). The work of Viviana Patti was partially carried out at the Universitat Politecnica de Valencia within the framework of a fellowship of the University of Turin co-funded by Fondazione CRT (WWS Program 2).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Web Service SWePT: A Hybrid Opinion Mining Approach

  • Baca-Gomez, Yolanda Raquel
  • Martínez, Alicia
  • Estrada Esquivel, Hugo
  • Hernandez-Farias, Delia Irazu
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] The increasing use of social networks and online sites where people can express their opinions has created a growing interest in Opinion Mining. One of the main tasks of Opinion Mining is to determine whether an opinion is positive or negative. Therefore, the role of the feelings expressed on the web has become crucial, mainly due to the concern of businesses and government to automatically identify the semantic orientation of the views of customers or citizens. This is also a concern, in the area of health to identify psychological disorders. This research focuses on the development of a web application called SWePT (Web Service for Polarity detection in Spanish Texts), which implements the Sequential Minimal Optimization (SMO) algorithm, extracting its features from an affective lexicon in Mexican Spanish. For this purpose, a corpus and an affective lexicon in Mexican Spanish were created. The experiments using three (positive, neutral, negative) and five categories (very positive, positive, neutral, negative, and very negative) allow us to demonstrate the effectiveness of the presented method. SWePT has also been implemented in the Emotion-bracelet interface, which shows the opinion of a user graphically., This work has been partially supported by the Sectorial Fund CONACyT-INEGI: Project with ref. 208471, INFOTEC, Mexico. And, also by the project CNDT-PYR2015-0016, CENIDET, Mexico. The work of the third author was in the framework of the SomEMBED MINECO TIN2015-71147-C2-1-P research project. The National Council for Science and Technology (CONACyT Mexico) has funded the research work of Delia Irazu Hernandez Farias (Grant No. 218109/313683 CVU-369616).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Overview of PAN 2018. Author identification, author profiling, and author obfuscation

  • Stamatatos, Efstathios
  • Rangel-Pardo, Francisco Manuel
  • Tschuggnall, Michael
  • Stein, Benno
  • Kestemont, Mike
  • Potthast, Martin
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] PAN 2018 explores several authorship analysis tasks enabling a systematic comparison of competitive approaches and advancing research in digital text forensics.More specifically, this edition of PAN introduces a shared task in cross-domain authorship attribution, where texts of known and unknown authorship belong to distinct domains, and another task in style change detection that distinguishes between single author and multi-author texts. In addition, a shared task in multimodal author profiling examines, for the first time, a combination of information from both texts and images posted by social media users to estimate their gender. Finally, the author obfuscation task studies how a text by a certain author can be paraphrased so that existing author identification tools are confused and cannot recognize the similarity with other texts of the same author. New corpora have been built to support these shared tasks. A relatively large number of software submissions (41 in total) was received and evaluated. Best paradigms are highlighted while baselines indicate the pros and cons of submitted approaches., The work at the Universitat Polit`ecnica de Val`encia was funded by the MINECO research project SomEMBED (TIN2015-71147-C2-1-P)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Overview of PAN&apos, 17: Author Identification, Author Profiling, and Author Obfuscation

  • Potthast, Martin
  • Rangel-Pardo, Francisco Manuel
  • Tschuggnall, Michael
  • Stamatatos, Efstathios
  • Stein, Benno
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] The PAN 2017 shared tasks on digital text forensics were held in conjunction with the annual CLEF conference. This paper gives a high-level overview of each of the three shared tasks organized this year, namely author identification, author profiling, and author obfuscation. For each task, we give a brief summary of the evaluation data, performance measures, and results obtained. Altogether, 29 participants submitted a total of 33 pieces of software for evaluation, whereas 4 participants submitted to more than one task. All submitted software has been deployed to the TIRA evaluation platform, where it remains hosted for reproducibility purposes., The work at the Universitat Politècnica de València was funded by the MINECO research project SomEMBED (TIN2015-71147-C2-1-P).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Arabic Cooperative Answer Generation via Wikipedia Article Infoboxes

  • Trigui, Omar
  • Belguith, Lamia
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] The typical question-answering system is facing many challenges related to the processing of questions and information resources in the extraction and generation of adequate answers. These challenges increase when the requested answer is cooperative and its language is Arabic. In this paper, we propose an original approach to generate cooperative answers for user-definitional questions designed to be integrated in a question-answering system. This approach is mainly based on the exploitation of the semi-structured Web knowledge which consists in using features derived from Wikipedia article infoboxes to generate cooperative answers. It is globally independent of a particular language, which gives it the ability to be integrated in any definitional question-answering system. We have chosen to integrate and experiment it in a definitional question-answering system dealing with the Arabic language entitled DefArabicQA. The results showed that this system has a significant impact on the approach efficiency regarding the improvement of the quality of the answer., The work of the third author was partially funded by the Spanish Ministry of Economy, Industry and Competitiveness (MINECO) under the SomEMBED research project (TIN2015-71147-C2-1-P) and by the Generalitat Valenciana under the grant ALMAMATER (PrometeoII/2014/030).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Irony Detection in Twitter: The Role of Affective Content

  • Hernandez-Farias, Delia Irazu
  • Patti, Viviana
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Irony has been proven to be pervasive in social media, posing a challenge to sentiment analysis systems. It is a creative linguistic phenomenon where affect-related aspects play a key role. In this work, we address the problem of detecting irony in tweets, casting it as a classification problem. We propose a novel model that explores the use of affective features based on a wide range of lexical resources available for English, reflecting different facets of affect. Classification experiments over different corpora show that affective information helps in distinguishing among ironic and nonironic tweets. Our model outperforms the state of the art in almost all cases., The National Council for Science and Technology (CONACyT Mexico) has funded the research work of Delia Irazu Hernandez Farias (Grant No. 218109/313683 CVU-369616). The work of Viviana Patti was partially carried out at the Universitat Politecnica de Valencia within the framework of a fellowship of the University of Turin cofunded by Fondazione CRT (World Wide Style Program 2). The work of Paolo Rosso has been partially funded by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the grant ALMAMATER (PrometeoII/2014/030).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A New Weighted k-Nearest Neighbor Algorithm Based on Newton¿s Gravitational Force

  • Aguilera, Juan
  • González, Luis C.
  • Montes-y-Gómez, Manuel
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] The kNN algorithm has three main advantages that make it appealing to the community: it is easy to understand, it regularly offers competitive performance and its structure can be easily tuning to adapting to the needs of researchers to achieve better results. One of the variations is weighting the instances based on their distance. In this paper we propose a weighting based on the Newton's gravitational force, so that a mass (or relevance) has to be assigned to each instance. We evaluated this idea in the kNN context over 13 benchmark data sets used for binary and multi-class classification experiments. Results in F1 score, statistically validated, suggest that our proposal outperforms the original version of kNN and is statistically competitive with the distance weighted kNN version as well., This research was partially supported by CONACYT-Mexico (project FC-2410). The work of Paolo Rosso has been partially funded by the SomEMBED TIN2015-71147-C2-1-P MINECO research project.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Deep Source-Context Feature for Lexical Selection in Statistical Machine Translation

  • Gupta, Parth Alokkumar
  • Costa-Jussa, Marta R
  • Banchs, Rafael
  • Rosso, Paolo|||0000-0002-8922-1242
This paper presents a methodology to address lexical disambiguation in a standard phrase-based statistical machine translation system. Similarity among source contexts is used to select appropriate translation units. The information is introduced as a novel feature of the phrase-based model and it is used to select the translation units extracted from the training sentence more similar to the sentence to translate. The similarity is computed through a deep autoencoder representation, which allows to obtain effective lowdimensional embedding of data and statistically significant BLEU score improvements on two different tasks (English-to-Spanish and English-to-Hindi). © 2016 Elsevier B.V. All rights reserved., The work of the first author has been supported by FPI UPV pre-doctoral grant (num. registro - 3505). The work of the second author has been supported by Spanish Ministerio de Economia y Competitividad, contract TEC2015-69266-P and the Seventh Framework Program of the European Commission through the International Outgoing Fellowship Marie Curie Action (IMTraP-2011-29951). The work of the third author has been supported by the Spanish Ministerio de Economia y Competitividad, SomEMBED TIN2015-71147-C2-1-P research project and by the Generalitat Valenciana under the grant ALMAPATER (PrometeoII/2014/030).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

ECIR 2016 Workshop on Modeling, Learning and Mining for Cross/Multilinguality (MultiLingMine 16)

  • Ienco, Dino
  • Roche, Mathieu
  • Romeo, Salvatore
  • Tagarelli, Andrea
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] The First International Workshop on Modeling, Learning and Mining for Cross/Multilinguality (MultiLingMine) was held in conjunction with the 2016 European Conference on Information Retrieval (ECIR), in Padua, Italy. This report presents an overview of the motivations and objectives underlying the establishment of this workshop. It also provides a summary of the contributing papers and of the main research topics and trends discussed among the participants., This work is partially funded by research project PON 2007-2013 “BA2Know - Business Analytics to Know”, funded by Italian Ministry of Instruction, University, and Research, and by the research project TIN2015-71147-C2-1-P of the Spanish Ministry of Economy and Competitiveness.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Cross-language Plagiarism Detection over Continuous-space- and Knowledge Graph-based Representations of Language

  • Franco-Salvador, Marc
  • Gupta, Parth Alokkumar
  • Banchs, Rafael
  • Rosso, Paolo|||0000-0002-8922-1242
Cross-language (CL) plagiarism detection aims at detecting plagiarised fragments of text among documents in different languages. The main research question of this work is on whether knowledge graph representations and continuous space representations can complement to each other and improve the state-of-the-art performance in CL plagiarism detection methods. In this sense, we propose and evaluate hybrid models to assess the semantic similarity of two segments of text in different languages. The proposed hybrid models combine knowledge graph representations with continuous space representations aiming at exploiting their complementarity in capturing different aspects of cross-lingual similarity. We also present the continuous word alignment-based similarity analysis, a new model to estimate similarity between text fragments. We compare the aforementioned approaches with several state-of-the-art models in the task of CL plagiarism detection and study their performance in detecting different length and obfuscation types of plagiarism cases. We conduct experiments over Spanish-English and GermanEnglish datasets. Experimental results show that continuous representations allow the continuous word alignment-based similarity analysis model to obtain competitive results and the knowledge-based document similarity model to outperform the state-of-the-art in CL plagiarism detection. © 2016 Elsevier B.V. All rights reserved., This research has been carried out in framework of the FPI-UPV pre-doctoral grant (No de registro - 3505) awarded to Parth Gupta and in the framework of the national projects DIANA-APPLICATIONS - Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01), and SomEMBED: SOcial Media language understanding - EMBEDing contexts (TIN2015-71147-C2-1-P). We would like to thank Martin Potthast, Daniel Ortiz-Martinez, and Luis A. Leiva for their support and comments during this research.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Knowledge-Based Weighted KNN for Detecting Irony in Twitter

  • Hernandez-Farias, Delia Irazu
  • Montes Gomez, Manuel
  • Escalante, Hugo
  • Patti, Viviana
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] In this work, we propose a variant of a well-known instancebased algorithm: WKNN. Our idea is to exploit task-dependent features in order to calculate the weight of the instances according to a novel paradigm: the Textual Attraction Force, that serves to quantify the degree of relatedness between documents. The proposed method was applied to a challenging text classification task: irony detection. We experimented with corpora in the state of the art. The obtained results show that despite being a simple approach, our method is competitive with respect to more advanced techniques., This research was funded by CONACYT project FC 2016-2410. The work of P. Rosso has been funded by the SomEMBED TIN2015-71147-C2-1-P MINECO research project. The work of V. Patti was partially funded by Progetto di Ateneo/CSP 2016 (IhatePrejudice, S1618_L2_BOSC_01).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Author Profiling in Social Media: The Impact of Emotions on Discourse Analysis

  • Rosso, Paolo|||0000-0002-8922-1242
  • Rangel-Pardo, Francisco Manuel
[EN] In this paper we summarise the content of the keynote that will be given at the 5th International Conference on Statistical Language and Speech Processing (SLSP) in Le Mans, France in October 23¿25, 2017. In the keynote we will address the importance of inferring demographic information for marketing and security reasons. The aim is to model how language is shared in gender and age groups taking into account its statistical usage. We will see how a shallow discourse analysis can be done on the basis of a graph-based representation in order to extract information such as how complicated the discourse is (i.e., how connected the graph is), how much interconnected grammatical categories are, how far a grammatical category is from others, how different grammatical categories are related to each other, how the discourse is modelled in different structural or stylistic units, what are the grammatical categories with the most central use in the discourse of a demographic group, what are the most common connectors in the linguistic structures used, etc. Moreover, we will see also the importance to consider emotions in the shallow discourse analysis and the impact that this has. We carried out some experiments for identifying gender and age, both in Spanish and in English, using PAN-AP-13 and PAN-PC-14 corpora, obtaining comparable results to the best performing systems of the PAN Lab at CLEF., The research work described in this paper was partially carried out in the framework of the SomEMBED project (TIN2015-71147-C2-1-P), funded by the Spanish Ministry of Economy, Industry and Competitiveness (MINECO).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Online Hate Speech against Women: Automatic Identification of Misogyny and Sexism on Twitter

  • Frenda, Simona
  • Ghanem, Bilal
  • Montes-y-Gómez, Manuel
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Patriarchal behavior, such as other social habits, has been transferred online, appearing as misogynistic and sexist comments, posts or tweets. This online hate speech against women has serious consequences in real life, and recently, various legal cases have arisen against social platforms that scarcely block the spread of hate messages towards individuals. In this difficult context, this paper presents an approach that is able to detect the two sides of patriarchal behavior, misogyny and sexism, analyzing three collections of English tweets, and obtaining promising results., The work of Simona Frenda and Paolo Rosso was partially funded by the Spanish MINECO under the research project SomEMBED (TIN2015-71147-C2-1-P). We also thank the support of CONACYT-Mexico (project FC-2410).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Capítulo o parte de un libro (BookPart)

Overview of the PAN&apos, 2016 - New Challenges for Authorship Analysis: Cross-genre Profiling, Clustering, Diarization, and Obfuscation

  • Rosso, Paolo|||0000-0002-8922-1242
  • Rangel-Pardo, Francisco Manuel
  • Potthast, Martin
  • Stamatatos, Efstathios
  • Tschuggnall, Michael
  • Stein, Benno
This paper presents an overview of the PAN/CLEF evaluation lab. During the last decade, PAN has been established as the main forum of digital text forensic research. PAN 2016 comprises three shared tasks: (i) author identification, addressing author clustering and diarization (or intrinsic plagiarism detection); (ii) author profiling, addressing age and gender prediction from a cross-genre perspective; and (iii) author obfuscation, addressing author masking and obfuscation evaluation. In total, 35 teams participated in all three shared tasks of PAN 2016 and, following the practice of previous editions, software submissions were required and evaluated within the TIRA experimentation framework., The work of the first author was partially supported by the Som EMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the grant ALMA MATER (Prometeo II/2014/030). The work of the second author was partially supported by Autoritas Consulting and by Ministerio de Economía y Competitividad de España under grant ECOPORTUNITY IPT-2012-1220-430000.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Improving Attitude Words Classification for Opinion Mining using Word Embedding

  • Ortega-Bueno, Reynier
  • Medina-Pagola, José E.
  • Muñiz-Cuza, Carlos Enrique
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Recognizing and classifying evaluative expressions is an important issue of sentiment analysis. This paper presents a corpus-based method for classifying attitude types (Affect, Judgment and Appreciation) and attitude orientation (positive and negative) of words in Spanish relying on the Attitude system of the Appraisal Theory. The main contribution lies in exploring large and unlabeled corpora using neural network word embedding techniques in order to obtain semantic information among words of the same attitude and orientation class. Experimental results show that the proposed method achieves a good effectiveness and outperforms the state of the art for automatic classification of attitude words in Spanish language., The work of the fourth author was partially supported by the SomEMBED TIN2015-71147-C2-1-P research project (MINECO/FEDER).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Paraphrase Plagiarism Identifcation with Character-level Features

  • Sánchez-Vega, Fernando
  • Villatoro-Tello, Esaú
  • Montes-y-Gómez, Manuel
  • Stamatatos, Efstathios
  • Villaseñor-Pineda, Luis
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Several methods have been proposed for determining plagiarism between pairs of sentences, passages or even full documents. However, the majority of these methods fail to reliably detect paraphrase plagiarism due to the high complexity of the task, even for human beings. Paraphrase plagiarism identi cation consists in automatically recognizing document fragments that contain re-used text, which is intentionally hidden by means of some rewording practices such as semantic equivalences, discursive changes, and morphological or lexical substitutions. Our main hypothesis establishes that the original author's writing style ngerprint prevails in the plagiarized text even when paraphrases occur. Thus, in this paper we propose a novel text representation scheme that gathers both content and style characteristics of texts, represented by means of character-level features. As an additional contribution, we describe the methodology followed for the construction of an appropriate corpus for the task of paraphrase plagiarism identi cation, which represents a new valuable resource to the NLP community for future research work in this field., This work is the result of the collaboration in the framework of the CONACYT Thematic Networks program (RedTTL Language Technologies Network) and the WIQ-EI IRSES project (Grant No. 269180) within the FP7 Marie Curie action. The first author was supported by CONACYT (Scholarship 258345/224483). The second, third, and sixth authors were partially supported by CONACyT (Project Grants 258588 and 2410). The work of the fourth author was partially supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the Grant ALMAMATER (PrometeoII/2014/030).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

El impacto de las emociones en el análisis de la polaridad en textos con lenguaje figurado en Twitter

  • Escortell Pérez, Mª Amparo
  • Gimenez Fayos, Maite
  • Rosso, Paolo|||0000-0002-8922-1242
[ES] Uno de los retos más complejos a los que se enfrenta el Procesamiento de Lenguaje Natural es el de determinar la polaridad de un tweet (positiva, negativa o neutra) cuando en éste aparece lenguaje figurado, es particularmente complejo en los textos cortos y agramaticales que podemos encontrar en las redes sociales. Este trabajo presenta un estudio exhaustivo sobre la capacidad de distintos recursos léxicos de emociones para analizar la polaridad de un conjunto de datos extraídos de Twitter, detallando el impacto de cada uno de los recursos sobre distintas formas de lenguaje figurado como pueden ser la ironía y el sarcasmo que encontramos profusamente en este corpus. Los resultados obtenidos muestran indicios que apuntan a que la inclusión de información relativa a las emociones ayuda a clasificar correctamente la polaridad tanto a nivel global como a nivel del lenguaje figurado o literal. Palabras clave: Análisis de sentimientos, emociones, lenguaje figurado, twitter, ironía, sarcasmo, semeval, polaridad, [EN] One of the most challenging tasks in Natural Language Processing is to determine the polarity of a tweet (positive, negative or neutral) when figurative language is present, especially in the short and ungrammatical texts that can be found in social media. In this paper we present a comprehensive study of the capacity of several emotional lexicons for Sentiment Analysis of Figurative Language in Twitter, detailing how each resource impacts on different figurative language devices such as sarcasm and irony. There are indications in our results that suggest that using emotional information improves the performance of a Sentiment Analysis model regardless of the presence or not of figurative language in the texts analyzed., Este trabajo se ha desarrollado en el marco del proyecto de investigación SomEMBED (TIN2015-71147-C2-1-P) del Ministerio de Economía y Sostenibilidad (MINECO). Asimismo, el trabajo de la segunda autora ha sido financiado a través del Programa de Ayudas de Investigación y Desarrollo de la Universitat Politècnica de València (PAID 2015).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Do Linguistic Features Help Deep Learning? The Case of Aggressiveness in Mexican Tweets

  • Frenda, Simona
  • Banerjee, Somnath
  • Patti, Viviana
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] In the last years, the control of online user generated content is becoming a priority, because of the increase of online aggressiveness and hate speech legal cases. Considering the complexity and the importance of this issue, this paper presents an approach that combines the deep learning framework with linguistic features for the recognition of aggressiveness in Mexican tweets. This approach has been evaluated relying on a collection of tweets released by the organizers of the shared task about aggressiveness detection in the context of the Ibereval 2018 evaluation campaign. The use of a benchmark corpus allows to compare the results with those obtained by Ibereval 2018 participant systems. However, looking at the achieved results, linguistic features seem not to help the deep learning classification for this task., The work of Simona Frenda and Paolo Rosso was partially funded by the Spanish MINECO under the research project SomEMBED (TIN2015-71147-C2-1-P).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A Low Dimensionality Representation for Language Variety Identification

  • Rangel-Pardo, Francisco Manuel
  • Franco-Salvador, Marc
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Language variety identification aims at labelling texts in a native language (e.g. Spanish, Portuguese, English) with its specific variation (e.g. Argentina, Chile, Mexico, Peru, Spain; Brazil, Portugal; UK, US). In this work we propose a low dimensionality representation (LDR) to address this task with five different varieties of Spanish: Argentina, Chile, Mexico, Peru and Spain. We compare our LDR method with common state-of-the-art representations and show an increase in accuracy of ~35%. Furthermore, we compare LDR with two reference distributed representation models. Experimental results show competitive performance while dramatically reducing the dimensionality¿and increasing the big data suitability¿to only 6 features per variety. Additionally, we analyse the behaviour of the employed machine learning algorithms and the most discriminating features. Finally, we employ an alternative dataset to test the robustness of our low dimensionality representation with another set of similar languages., The work of the first author was in the framework of ECOPORTUNITY IPT-2012-1220-430000. The work of the last two authors was in the framework of the SomEMBED MINECO TIN2015-71147-C2-1-P research project. This work has been also supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the grant ALMAPATER (PrometeoII/2014/030).
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Irony and Sarcasm Detection in Twitter: The Role of Affective Content, Detección de Ironía y Sarcasmo en Twitter: La Función del Contenido Afectivo

  • Hernández Farías, Delia Irazú
Tesis doctoral en Informática realizada por Delia Irazú Hernández Farías y dirigida por el Dr. Paolo Rosso (Universitat Politècnica de València) y la Dra. Viviana Patti (University of Turin) en el marco de un convenio de cotutela entre la Universitat Politècnica de València, España y la Universidad de Turin, Italia. La defensa de la tesis fue en Valencia, España el 25 de septiembre de 2017 ante un tribunal compuesto por: Horacio Saggion (Universitat Pompeu Fabra), Elisabetta Fersini (Università degli Studi di Milano-Bicocca) y Roberto Basili (Univerità di Roma Tor Vergata). Se obtuvo la mención internacional tras una estancia de 12 meses en la Universidad de Turin.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

El impacto de las emociones en el análisis de la polaridad en textos con lenguaje figurado en Twitter, The Impact of Emotions on Polarity Analysis using Figurative Language in Twitter

  • Escortell Pérez, María Amparo
  • Giménez Fayos, Maite
  • Rosso, Paolo
Uno de los retos más complejos a los que se enfrenta el Procesamiento de Lenguaje Natural es el de determinar la polaridad de un tweet (positiva, negativa o neutra) cuando en éste aparece lenguaje figurado, es particularmente complejo en los textos cortos y agramaticales que podemos encontrar en las redes sociales. Este trabajo presenta un estudio exhaustivo sobre la capacidad de distintos recursos léxicos de emociones para analizar la polaridad de un conjunto de datos extraídos de Twitter, detallando el impacto de cada uno de los recursos sobre distintas formas de lenguaje figurado como pueden ser la ironía y el sarcasmo que encontramos profusamente en este corpus. Los resultados obtenidos muestran indicios que apuntan a que la inclusión de información relativa a las emociones ayuda a clasificar correctamente la polaridad tanto a nivel global como a nivel del lenguaje figurado o literal.