Skip to main content

DIANA-APPLICATIONS: FINDING HIDDEN KNOWLEDGE IN TEXTS: APPLICATIONS

TIN2012-38603-C02-01

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Nacional de Proyectos de Investigación Fundamental
Subprogram Subprograma de Proyectos de Investigación Fundamental no Orientada
Call Proyectos I+D
Call year 2012
State Plan 2008-2011 Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica
Management unit Secretaría de Estado de Investigación, Desarrollo e Innovación
Beneficiary centre UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 33
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Construction of an ontology for intelligent Arabic QA systems leveraging the Conceptual Graphs representation

  • Abouenour, Lahsen
  • Nasri, Mohamed
  • Bouzoubaa, Karim
  • Kabbaj, Adil
  • Rosso, Paolo|||0000-0002-8922-1242
The last decade had known a great interest in Arabic Natural Language Processing (NLP) applications. This interest is due to the prominent importance of this 6th most wide-spread language in the world with more than 350 million native speakers. Currently, some basic Arabic language challenges related to the high inflection and derivation, Part-of-Speech (PoS) tagging, and diacritical ambiguity of Arabic text are practically tamed to a great extent. However, the development of high level and intelligent applications such as Question Answering (QA) systems is still obstructed by the lacks in terms of ontologies and other semantic resources. In this paper, we present the construction of a new Arabic ontology leveraging the contents of Arabic WordNet (AWN) and Arabic VerbNet (AVN). This new resource presents the advantage to combine the high lexical coverage and semantic relations between words existing in AWN together with the formal representation of syntactic and semantic frames corresponding to verbs in AVN. The Conceptual Graphs representation was adopted in the framework of a multi-layer platform dedicated to the development of intelligent and multi-agents systems. The built ontology is used to represent key concepts in questions and documents for further semantic comparison. Experiments conducted in the context of the QA task show a promising coverage with respect to the processed questions and passages. The obtained results also highlight an improvement in the performance of Arabic QA regarding the c@1 measure., The work of the last author was carried out in the framework of the WIQ-EI IRSES project (Grant No. 269180) within the FP 7 Marie Curie, the DIANA APPLICATIONS - Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Counting co-occurrences in citations to identify plagiarised text fragments

  • Pertile, Solange de Lurdes
  • Moreira, Viviane P.
  • Rosso, Paolo|||0000-0002-8922-1242
Research in external plagiarism detection is mainly concerned with the comparison of the textual contents of a suspicious document against the contents of a collection of original documents. More recently, methods that try to detect plagiarism based on citation patterns have been proposed. These methods are particularly useful for detecting plagiarism in scientific publications. In this work, we assess the value of identifying co-occurrences in citations by checking whether this method can identify cases of plagiarism in a dataset of scientific papers. Our results show that most the cases in which co-occurrences were found indeed correspond to plagiarised passages, This work was partially funded by CNPq (478979/2012-6). Solange Pertile’s 5-month internship at NLE Lab of Universitat Polit`ecnica de Val`encia was funded by CAPES. P.Rosso’s work was carried out in the framework of the the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems and the European Commission WIQ-EI IRSES (no. 269180) and DIANA-APPLICATIONSFinding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) research projects. We thank the authors of [5] for sharing their dataset with us and Enrique Flores for the preliminary brainstorming on how to identify co-occurrences in citations
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Overview of the Author Profiling Task at PAN 2013

  • Rangel, Francisco
  • Koppel, Moshe
  • Stamatatos, Efstathios
  • Inches, Giacomo
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] This overview presents the framework and results for the Author Profiling task at PAN 2013. We describe in detail the corpus and its characteristics, and the evaluation framework we used to measure the participants performance to solve the problem of identifying age and gender from anonymous texts. Finally, the approaches of the 21 participants and their results are described., The author profiling task @PAN-2013 was an activity of the WIQ-EI IRSES project (Grant No. 269180) within the FP 7 Marie Curie People Framework of the European Commission. We want to thank the Forensic Lab of the Universitat Pompeu Fabra Barcelona for sponsoring the award for the winner team. The work of the first author was partially funded by Autoritas Consulting SA and by Ministerio de Economía y Competitividad de España under grant ECOPORTUNITY IPT-2012-1220-430000. The work of the second author was in the framework the DIANA-APPLICATIONS-Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems. The work of fifth author was funded in part by the Swiss National Science Foundation (SNF) project "Mining Conversational Content for Topic Modelling and Author Identification (ChatMiner)" under grant number 200021_130208.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Overview of the 2nd Author Profiling Task at PAN 2014

  • Rangel, Francisco
  • Chrugur, irina
  • Potthast, Martin
  • Trenkmann, Martin
  • Stein, Benno
  • Verhoeven, Ben
  • Daelemans, Walter
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] This overview presents the framework and the results for the Author Profiling task at PAN 2014. Objective of this year is the analysis of the adaptability of the detection approaches when given different genres. For this purpose a corpus with four different parts (subcorpora) has been compiled: social media, Twitter, blogs, and hotel reviews. The construction of the Twitter subcorpus happened in cooperation with RepLab in order to investigate also a reputational perspective. Altogether, the approaches of 10 participants are evaluated., The PAN task on author profiling has been organised in the framework of the WIQ-EI IRSES project (Grant No. 269180) within the FP 7 Marie Curie People Framework of the European Commission. We would like to thank Atribus by Corex for sponsoring the award for the winner team. We thank Julio Gonzalo, Jorge Carrillo and Damiano Spina from UNED for helping with the Twitter subcorpus. The work of the first author was partially funded by Autoritas Consulting SA and by Ministerio de Economía y Competitividad de España under grant ECOPORTUNITY IPT-2012-1220-430000 and CSO2013-43054-R. The work of the second author was in the framework the DIANA-APPLICATIONS-Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Utilisation des CACs et des Ressources Externes pour l Amélioration des Performances de l Étiquetage Morphosyntaxique

  • Outahajala, Mohamed
  • Benajiba, Yassine
  • Rosso, Paolo|||0000-0002-8922-1242
[FR] La langue amazighe, comme la plupart des langues de moindre diffusion, souffre encore de la pénurie d'outils et des ressources pour son traitement automatique en particulier les corpus annotés. Ces derniers sont plus difficiles à construire que les corpus bruts qui à leur tour nécessitent des prétraitements dans la majorité des cas. L’objectif de cet article est de présenter une approche basée sur l’apprentissage semisupervisé visant l’utilisation d’un corpus de textes brutes, sélectionnées sur la base de la mesure de confiance des Champs Aléatoires Conditionnels(CACs), conjointement avec un corpus annoté manuellement de 20k morphèmes. Les résultats des expérimentations préliminaires montrent une réduction du taux d’erreur de l’étiqueteur morphosyntaxique de 1,3%. Aussi la réduction du taux d’erreur est de 5,9%, entre 60% et 90% du corpus, lorsque le modèle est entrainé par les phrases du corpus brut annotées automatiquement., [EN] Amazigh language, and like most of the languages which have only recently started being investigated for the Natural Language Processing (NLP) tasks, lacks annotated corpora and tools and still suffers from the scarcity of linguistic tools and resources and especially annotated corpora. Creating labeled data is a hard task. However, obtaining unlabeled data, although needing most time preprocessing for languages with scarce resources, is less difficult. The aim of this paper is to present a semi-supervised based approach using labeled and unlabeled data. Preliminary results show an error reduction of 1,3%, when training our POS tagger with Conditional Random Fields(CRFs), with chosen automatically annotated texts and a small manually annotated corpus of about 20k tokens. Also, when trained with automatically annotated data, the achieved improvement between 60% and 90% of the trained data is 5.9%., Le premier auteur exprime sa gratitude à la CODESRIA. Les travaux du quatrième auteur ont été financés dans le cadre des projets de recherche: VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems, la commission européenne WIQ-EI IRSES (no. 269180) et DIANAAPPLICATIONS(TIN2012-38603-C02-01).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Impacto de la ironía en la minería de opiniones basada en un léxico afectivo

  • Baca Gomez, Yolanda Raquel
  • Castro Sánchez, Noé Alejandro
  • Martinez, Alicia
  • Hernández Farias, Delia Irazu
  • Rosso, Paolo|||0000-0002-8922-1242
[ES] En este art´ıculo se describe un m´etodo sistem´atico que identifica la polaridad de textos en Espa˜nol, as´ı como el impacto de la iron´ıa en la miner´ıa de opiniones. Se propone una aproximaci´on basada en un aprendizaje autom´atico y en la extracci´on de caracter´ısticas a partir de un L´exico Afectivo en Espa˜nol. Fue necesaria la creaci´on de un corpus para el entrenamiento y evaluaci´on del m´etodo propuesto. Los resultados experimentales muestran que la iron´ıa tiene un impacto negativo en la evaluaci´on realizada, Esta investigaci´on ha sido financiada por el proyecto DGEST con N´um. Ref.: 5049-13-P, Programa CONACYT (290842), (218109/313683) y los proyectos DIANA- APPLICATIONS (TIN2012-38603-C02-01) y WIQEI IRSES (Grant No. 269180; FP 7 Marie Curie People).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Cross-language source code re-use detection using latent semantic analysis

  • Flores Sáez, Enrique
  • Barrón-Cedeño, Luis Alberto
  • Moreno Boronat, Lidia Ana
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Nowadays, Internet is the main source to get information from blogs, encyclopedias, discussion forums, source code repositories, and more resources which are available just one click away. The temptation to re-use these materials is very high. Even source codes are easily available through a simple search on the Web. There is a need of detecting potential instances of source code re-use. Source code re-use detection has usually been approached comparing source codes in their compiled version. When dealing with cross-language source code re-use, traditional pproaches can deal only with the programming languages supported by the compiler. We assume that a source code is a piece of text ,with its syntax and structure, so we aim at applying models for free text re-use detection to source code. In this paper we compare a Latent Semantic Analysis (LSA) approach with previously used text re-use detection models for measuring cross-language similarity in source code. The LSA-based approach shows slightly better results than the other models, being able to distinguish between re-used and related source codes with a high performance., This work was partially supported by Universitat Polit`ecnica de Val`encia, WIQ-EI (IRSES grant n. 269180), and DIANA-APPLICATIONS (TIN2012- 38603-C02- 01) project. The work of the fourth author is also supported by VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

TWIN: Personality-based Intelligent Recommender System

  • Roshchina, Alexandra
  • Cardiff, John
  • Rosso, Paolo|||0000-0002-8922-1242
This paper presents the Tell me What I Need (TWIN) Personality-based Intelligent Recommender System, the goal of which is to recommend items chosen by like-minded (or twin ) people with similar personality types which we estimate from their writings. In order to produce recommendations it applies the results achieved in the personality from the text recognition research field to Personality-based Recommender System user profile modelling. In this way it creates a bridge between the efforts of automatic personality score estimation from plain text and the field of Intelligent Recommender Systems. The paper describes the TWIN system architecture, and results of the experimentation with the system in the online travelling domain in order to investigate the possibility of providing valuable recommendations of hotels of the TripAdvisor website for like-minded people . The results compare favourably with related experiments, although they demonstrate the complexity of this challenging task., The research work of the third author is partially funded by the WIQ-EI (IRSES grant n. 269180) and DIANA APPLICATIONS (TIN2012-38603-C02-01), and done in the framework of the VLC/Campus Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

A Comparison of Approaches for Measuring Cross-Lingual Similarity of Wikipedia Articles

  • Barrón Cedeño, Luis Alberto
  • Paramita, Monica Lestari
  • Clough, Paul
  • Rosso, Paolo|||0000-0002-8922-1242
Wikipedia has been used as a source of comparable texts for a range of tasks, such as Statistical Machine Translation and CrossLanguage Information Retrieval. Articles written in different languages on the same topic are often connected through inter-language-links. However, the extent to which these articles are similar is highly variable and this may impact on the use of Wikipedia as a comparable resource. In this paper we compare various language-independent methods for measuring cross-lingual similarity: character n-grams, cognateness, word count ratio, and an approach based on outlinks. These approaches are compared against a baseline utilising MT resources. Measures are also compared to human judgements of similarity using a manually created resource containing 700 pairs of Wikipedia articles (in 7 language pairs). Results indicate that a combination of language-independent models (char-ngrams, outlinks and word-count ratio) is highly effective for identifying cross-lingual similarity and performs comparably to language-dependent models (translation and monolingual analysis)., The work of the first author was in the framework of the Tacardi research project (TIN2012-38523-C02-00). The work of the fourth author was in the framework of the DIANA-Applications (TIN2012-38603-C02-01) and WIQ-EI IRSES (FP7 Marie Curie No. 269180) research projects.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

On the difficulty of automatically detecting irony: beyond a simple case of negation

  • Reyes Pérez, Antonio
  • Rosso, Paolo|||0000-0002-8922-1242
It is well known that irony is one of the most subtle devices used to, in a refined way and without a negation marker, deny what is literally said. As such, its automatic detection would represent valuable knowledge regarding tasks as diverse as sentiment analysis, information extraction, or decision making. The research described in this article is focused on identifying key values of components to represent underlying characteristics of this linguistic phenomenon. In the absence of a negation marker, we focus on representing the core of irony by means of three conceptual layers. These layers involve 8 different textual features. By representing four available data sets with these features, we try to find hints about how to deal with this unexplored task from a computational point of view. Our findings are assessed by human annotators in two strata: isolated sentences and entire documents. The results show how complex and subjective the task of automatically detecting irony could be., The research work of Paolo Rosso was done in the framework of the European Commission WIQ-EI Web Information Quality Evaluation Initiative (IRSES grant no. 269180) project within the FP 7 Marie Curie People, the DIANA-APPLICATIONS - Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

A hybrid approach for transliterated word-level language identification: CRF with post processing heuristics

  • Banerjee, Somnath
  • Kuila, Alapan
  • Roy, Aniruddha
  • Naskar, Sudip Kumar
  • Bandyopadhyay, Sivaji
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] In this paper, we describe a hybrid approach for word-level language (WLL) identification of Bangla words written in Roman script and mixed with English words as part of our participation in the shared task on transliterated search at Forum for Information Retrieval Evaluation (FIRE) in 2014. A CRF based machine learning model and post-processing heuristics are employed for the WLL identification task. In addition to language identification, two transliteration systems were built to transliterate detected Bangla words written in Roman script into native Bangla script. The system demonstrated an overall token level language identification accuracy of 0.905. The token level Bangla and English language identification F-scores are 0.899, 0.920 respectively. The two transliteration systems achieved accuracies of 0.062 and 0.037. The word-level language identification system presented in this paper resulted in the best scores across almost all metrics among all the participating systems for the Bangla-English language pair., We acknowledge the support of the Department of Electronics and Information Technology (DeitY), Government of India, through the project “CLIA System Phase II”. The research work of the last author was carried out in the framework of WIQ-EI IRSES (Grant No. 269180) within the FP 7 Marie Curie, DIANA-APPLICATIONS (TIN2012-38603-C02-01) projects and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

PAN@FIRE: Overview of SOCO Track on the Detection of SOurce COde Re-use

  • Flores Sáez, Enrique
  • Moreno Boronat, Lidia Ana
  • Villatoro-Tello, Esaú
  • Rosso, Paolo|||0000-0002-8922-1242
This paper summarizes the goals, organization and results of the first SOCO competitive evaluation campaign for systems that automatically detect the source code re-use phenomenon. The detection of source code re-use is an important research field for both software industry and academia fields. Accordingly, PAN@FIRE task, named SOurce COde Re-use (SOCO); focused on the detection of re-used source codes in C/C++ and Java programming languages. Participant systems were asked to annotate several source codes whether or not they represent cases of source code re-use. In total three teams participated and submitted 13 runs. The training set consisted of annotations made by several experts, a feature which turns the SOCO 2014 collection in a useful data set for future evaluations and, at the same time, it establishes a standard evaluation framework for future research works., PAN@FIRE (SOCO) has been organised in the framework of WIQ-EI (ECIRSES grant n. 269180) and DIANA-APPLICATIONS (TIN2012-38603-C02-01) research projects. The work of the last author was supported by CONACyT Mexico Project Grant CB-2010/153315, and SEP-PROMEP UAM-PTC-380/48510349.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

On the detection of SOurce COde re-use

  • Flores Sáez, Enrique
  • Moreno Boronat, Lidia Ana
  • Villatoro-Tello, Esaú
  • Rosso, Paolo|||0000-0002-8922-1242
This paper summarizes the goals, organization and results of the first SOCO competitive evaluation campaign for systems that automatically detect the source code re-use phenomenon. The detection of source code re-use is an important research field for both software industry and academia fields. Accordingly, PAN@FIRE track, named SOurce COde Re-use (SOCO) focused on the detection of re-used source codes in C/C++ and Java programming languages. Participant systems were asked to annotate several source codes whether or not they represent cases of source code re-use. In total five teams submitted 17 runs. The training set consisted of annotations made by several experts, a feature which turns the SOCO 2014 collection in a useful data set for future evaluations and, at the same time, it establishes a standard evaluation framework for future research works on the posed shared task., PAN@FIRE (SOCO) has been organised in the framework of WIQ-EI (EC IRSES grantn. 269180) and DIANA-APPLICATIONS (TIN2012-38603-C02- 01) research projects. The work of the last author was supported by CONACyT Mexico Project Grant CB-2010/153315, and SEP-PROMEP UAM-PTC-380/48510349.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Towards a Protein-Protein Interaction information extraction system: recognizing named entities

  • Danger Mercaderes, Roxana María
  • Pla Santamaría, Ferran
  • Molina Marco, Antonio|||0000-0001-6537-8803
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] The majority of biological functions of any living being are related to Protein Protein Interactions (PPI). PPI discoveries are reported in form of research publications whose volume grows day after day. Consequently, automatic PPI information extraction systems are a pressing need for biologists. In this paper we are mainly concerned with the named entity detection module of PPIES (the PPI information extraction system we are implementing) which recognizes twelve entity types relevant in PPI context. It is composed of two sub-modules: a dictionary look-up with extensive normalization and acronym detection, and a Conditional Random Field classifier. The dictionary look-up module has been tested with Interaction Method Task (IMT), and it improves by approximately 10% the current solutions that do not use Machine Learning (ML). The second module has been used to create a classifier using the Joint Workshop on Natural Language Processing in Biomedicine and its Applications (JNLPBA 04) data set. It does not use any external resources, or complex or ad hoc post-processing, and obtains 77.25%, 75.04% and 76.13 for precision, recall, and F1-measure, respectively, improving all previous results obtained for this data set., This work has been funded by MICINN, Spain, as part of the "Juan de la Cierva" Program and the Project DIANA-Applications (TIN2012-38603-C02-01), as well as the by the European Commission as part of the WIQ-EI IRSES Project (Grant No. 269180) within the FP 7 Marie Curie People Framework.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Using confidence and informativeness criteria to improve POS-tagging in amazigh

  • Outahajala, Mohamed
  • Benajiba, Yassine
  • Zenkouar, Lahbib
  • Rosso, Paolo|||0000-0002-8922-1242
Amazigh is used by tens of millions of people mainly for oral communication. However, and like all the newly investigated languages in natural language processing, it is resource-scarce. The main aim of this paper is to present our POS taggers results based on two state of the art sequence labeling techniques, namely Conditional Random Fields and Support Vector Machines, by making use of a small manually annotated corpus of only 20k tokens. Since creating labeled data is very time-consuming task while obtaining unlabeled data is less so, we have decided to gather a set of unlabeled data of Amazigh language that we have preprocessed and tokenized. The paper is also meant to address using semi-supervised techniques to improve POS tagging accuracy. An adapted self training algorithm, combining confidence measure with a function of Out Of Vocabulary words to select data for self training, has been used. Using this language independent method, we have managed to obtain encouraging results., The first author wants to grant CODESRIA. The work of the third author was carried out in the framework of the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems and the European Commission WIQ-EI IRSES (no. 269180) and DIANA-APPLICATIONS-Finding Hidden Knowledge in Texts: Applications(TIN2012-38603- C02-01) research projects.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

On the Identification of Emotions and Authors&apos, Gender in Facebook Comments on the Basis of their Writing Style

  • Rangel, Francisco
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] In this paper, we propose a method for automatic identifying emotions in written texts in social media with high proliferation such as Facebook. For that task we try to model the way people use the language to express themselves, and also use this model for identifying the gender of the authors. We focused on Spanish due to the lack of studies and resources in that language., The work of the first author was partially funded by Autoritas Consulting SA and by Ministerio de Econom´ıa de Espa˜na under grant ECOPORTUNITY IPT-2012-1220-430000. The work of the second author was carried out in the framework of the WIQ-EI IRSES project (Grant No. 269180) within the FP 7 Marie Curie, the DIANA APPLICATIONS Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

On the Impact of Emotions on Author Profiling

  • Rangel-Pardo, Francisco Manuel
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] In this paper, we investigate the impact of emotions on author profiling, concretely identifying age and gender. Firstly, we propose the EmoGraph method for modelling the way people use the language to express themselves on the basis of an emotion-labelled graph. We apply this representation model for identifying gender and age in the Spanish partition of the PAN-AP-13 corpus, obtaining comparable results to the best performing systems of the PAN Lab of CLEF. © 2015 Elsevier B.V. All rights reserved., The work of the first author was partially funded by Autoritas Consulting SA and by Spanish Ministry of Economics under grant ECOPORTUNITY IPT-2012-1220-430000. The work of the second author was carried out in the framework of the WIQ-EI IRSES project (Grant No. 269180) within the FP 7 Marie Curie, the DIANA APPLICATIONS: Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems. A special mention to Maria Dolores Rangel Pardo for her linguistic contribution to this investigation.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Cross-domain polarity classification using a knowledge-enhanced meta-classifier

  • Franco-Salvador, Marc
  • Cruz, Fermín L.
  • Troyano Jiménez, José Antonio
  • Rosso, Paolo|||0000-0002-8922-1242
In this paper, we propose the use of meta-learning to combine and enrich those approaches by adding also other knowledge-based features. In addition to the aforementioned classical approaches, our system uses the BabelNet multilingual semantic network to generate features derived from word sense disambiguation and vocabulary expansion. Experimental results show state-of-theart performance on single and cross-domain polarity classification., This research has been carried out in the framework of the European Commission WIQ-EI IRSES (No. 269180) and DIANA-APPLICATIONS - Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) projects. This research is partially funded by the national project ACOGEUS (TIN2012-38536-C03-02) and the regional project AORESCU (P11-TIC-7684 MO). We thank Juan M. Cotelo and Luis A. Leiva for their support and comments.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Knowledge Graphs as Context Models: Improving the Detection of Cross-Language Plagiarism with Paraphrasing

  • Franco-Salvador, Marc
  • Gupta, Parth
  • Rosso, Paolo|||0000-0002-8922-1242
Cross-language plagiarism detection attempts to identify and extract automatically plagiarism among documents in different languages. Plagiarized fragments can be translated verbatim copies or may alter their structure to hide the copying, which is known as paraphrasing and is more difficult to detect. In order to improve the paraphrasing detection, we use a knowledge graph-based approach to obtain and compare context models of document fragments in different languages. Experimental results in German-English and Spanish-English cross-language plagiarism detection indicate that our knowledge graph-based approach offers a better performance compared to other state-of-the-art models., The research has been carried out in the framework of the European Commission WIQ-EIIRSES (no. 269180) and DIANA-APPLICATIONS - Finding Hidden Knowledge in Texts:Applications (TIN2012-38603-C02-01) projects as well as the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Squeezing Bottlenecks: Exploring the Limits of Autoencoder Semantic Representation Capabilities

  • Gupta, Parth Alokkumar
  • Banchs, Rafael
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] We present a comprehensive study on the use of autoencoders for modelling text data, in which (differently from previous studies) we focus our attention on the various issues. We explore the suitability of two different models binary deep autencoders (bDA) and replicated-softmax deep autencoders (rsDA) for constructing deep autoencoders for text data at the sentence level. We propose and evaluate two novel metrics for better assessing the text-reconstruction capabilities of autoencoders. We propose an automatic method to find the critical bottleneck dimensionality for text representations (below which structural information is lost); and finally we conduct a comparative evaluation across different languages, exploring the regions of critical bottleneck dimensionality and its relationship to language perplexity. & 2015 Elsevier B.V. All rights reserved., A significant part of this research work was conducted during the first author's attachment to the HLT department of I2R in Singapore. The work of the first and third authors was carried out in the framework of the WIQ-EI IRSES project (Grant no. 269180) within the FP 7 Marie Curie, the DIANA APPLICATIONS Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Weblog and short text feature extraction and impact on categorisation

  • Perez Tellez, Fernando
  • Cardiff, John
  • Pinto Avendaño, David Eduardo
  • Rosso, Paolo|||0000-0002-8922-1242
The characterisation and categorisation of weblogs and other short texts has become an important research theme in the areas of topic/trend detection, and pattern recognition, amongst others. The value of analysing and characterising short text is to understand and identify the features that can identify and distinguish them, thereby improving input to the classification process. In this research work, we analyse a large number of text features and establish which combinations are useful to discriminate between the different genres of short text. Having identified the most promising features, we then confirm our findings by performing the categorisation task using three approaches: the Gaussian and SVM classifiers and the K-means clustering algorithm. Several hundred combinations of features were analysed in order to identify the best combinations and the results confirmed the observations made. The novel aspect of our work is the detection of the best combination of individual metrics which are identified as potential features to be used for the categorisation process., The research work of the third author is partially funded by the WIQ-EI (IRSES grant n. 269180) and DIANA APPLICATIONS (TIN2012-38603-C02-01), and done in the framework of the VLC/Campus Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Author Profiling and Plagiarism Detection

  • Rosso, Paolo|||0000-0002-8922-1242
In this chapter we introduce the topics that we will cover in the RuSSIR 2014 course on Author Profiling and Plagiarism Detection (APPD). Author profiling distinguishes between classes of authors studying how language is shared by classes of people. This task helps in identifying profiling aspects such as gender, age, native language, or even personality type. In case of the plagiarism detection task we are not interested in studying how language is shared. On the contrary, given a document we are interested in investigating if the writing style changes in order to unveil text inconsistencies, i.e., unexpected irregularities through the document such as changes in vocabulary, style and text complexity. In fact, when it is not possible to retrieve the source document(s) where plagiarism has been committed from, the intrinsic analysis of the suspicious document is the only way to find evidence of plagiarism. The difficulty in retrieving the source of plagiarism could be due to the fact that the documents are not available on the web or the plagiarised text fragments were obfuscated via paraphrasing or translation (in case the source document was in another language). In this overview, we also discuss the results of the shared tasks on author profiling (gender and age identification) and plagiarism detection that we help to organise at the PAN Lab on Uncovering Plagiarism, Authorship, and Social Software Misuse., The PAN shared tasks on author profil-ing and on plagiarism detection have been organised in the framework of the WIQ-EIIRSES project (Grant No. 269180) within the EC FP 7 Marie Curie People. The research work described in the paper was carried out in the framework of the DIANA-APPLICATIONS-Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction inIntelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication 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
Publication Artículo científico (JournalArticle)

Detecting Positive and Negative Deceptive Opinions using PU-learning

  • Hernández Fusilier, Donato
  • Montes Gómez, Manuel
  • Guzmán Cabrera, Rafael
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Nowadays a large number of opinion reviews are posted on the Web. Such reviews are a very important source of information for customers and companies. The former rely more than ever on online reviews to make their purchase decisions, and the latter to respond promptly to their clients’ expectations. Unfortunately, due to the business that is behind, there is an increasing number of deceptive opinions, that is, fictitious opinions that have been deliberately written to sound authentic, in order to deceive the consumers promoting a low quality product (positive deceptive opinions) or criticizing a potentially good quality one (negative deceptive opinions). In this paper we focus on the detection of both types of deceptive opinions, positive and negative. Due to the scarcity of examples of deceptive opinions, we propose to approach the problem of the detection of deceptive opinions employing PU-learning. PU-learning is a semi-supervised technique for building a binary classifier on the basis of positive (i.e., deceptive opinions) and unlabeled examples only. Concretely, we propose a novel method that with respect to its original version is much more conservative at the moment of selecting the negative examples (i.e., not deceptive opinions) from the unlabeled ones. The obtained results show that the proposed PU-learning method consistently outperformed the original PU-learning approach. In particular, results show an average improvement of 8.2% and 1.6% over the original approach in the detection of positive and negative deceptive opinions respectively. 2014 Elsevier Ltd. All rights reserved., This work is the result of the collaboration in the framework of the WIQEI IRSES project (Grant No. 269180) within the FP 7 Marie Curie. The work of the third author was in the framework the DIANA-APPLICATIONS-Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Detection of opinion spam with character n-grams

  • Hernández Fusilier, Donato
  • Montes Gomez, Manuel
  • Guzmán Cabrera, Rafael
  • Rosso, Paolo|||0000-0002-8922-1242
In this paper we consider the detection of opinion spam as a stylistic classi cation task because, given a particular domain, the deceptive and truthful opinions are similar in content but di ffer in the way opinions are written (style). Particularly, we propose using character ngrams as features since they have shown to capture lexical content as well as stylistic information. We evaluated our approach on a standard corpus composed of 1600 hotel reviews, considering positive and negative reviews. We compared the results obtained with character n-grams against the ones with word n-grams. Moreover, we evaluated the e ffectiveness of character n-grams decreasing the training set size in order to simulate real training conditions. The results obtained show that character n-grams are good features for the detection of opinion spam; they seem to be able to capture better than word n-grams the content of deceptive opinions and the writing style of the deceiver. In particular, results show an improvement of 2:3% and 2:1% over the word-based representations in the detection of positive and negative deceptive opinions respectively. Furthermore, character n-grams allow to obtain a good performance also with a very small training corpus. Using only 25% of the training set, a Na ve Bayes classi er showed F1 values up to 0.80 for both opinion polarities., This work is the result of the collaboration in the frame-work of the WIQEI IRSES project (Grant No. 269180) within the FP7 Marie Curie. The second author was partially supported by the LACCIR programme under project ID R1212LAC006. Accordingly, the work of the third author was in the framework the DIANA-APPLICATIONS-Finding Hidden Knowledge inTexts: Applications (TIN2012-38603-C02-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Sentiment Analysis in Twitter for Spanish

  • Pla Santamaría, Ferran
  • Hurtado Oliver, Lluis Felip|||0000-0002-1877-0455
This paper describes a SVM-approach for Sentiment Analysis (SA) in Twitter for Spanish. This task was part of the TASS2013 workshop, which is a framework for SA that is focused on the Spanish language. We describe the approach used, and we present an experimental comparison of the approaches presented by the di erent teams that took part in the competition. We also describe the improvements that were added to our system after our participation in the competition. With these improvements, we obtained an accuracy of 62.88% and 70.25% on the SA test set for 5-level and 3-level tasks respectively. To our knowledge, these results are the best results published until now for the SA tasks of the TASS2013 workshop., This work has been funded by the projects, DIANA (MEC TIN2012-38603-C02-01) and Tímpano (MEC TIN2011-28169-C05-01).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Capítulo o parte de un libro (BookPart)

Applying basic features from sentiment analysis on automatic irony detection

  • Hernández Farías, Irazú
  • Benedí Ruiz, José Miguel
  • Rosso, Paolo|||0000-0002-8922-1242
People use social media to express their opinions. Often linguistic devices such as irony are used. From the sentiment analysis perspective such utterances represent a challenge being a polarity reversor (usually from positive to negative). This paper presents an approach to address irony detection from a machine learning perspective. Our model considers structural features as well as, for the first time, sentiment analysis features such as the overall sentiment of a tweet and a score of its polarity. The approach has been evaluated over a set classifiers such as: Naïve Bayes, Decision Tree, Maximum Entropy, Support Vector Machine, and for the first time in irony detection task: Multilayer Perceptron. The results obtained showed the ability of our model to distinguish between potentially ironic and non-ironic sentences., The National Council for Science and Technology (CONACyT Mexico) has funded the research work of the first author (Grant No.218109/313683, CVU-369616). The research work of third author was carried out inthe framework of WIQ-EI IRSES (Grant No. 269180) within the FP 7 Marie Curie, DIANA-APPLICATIONS (TIN2012-38603-C02-01) projects and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Emotion and Sentiment in Social and Expressive Media: Introduction to the special issue

  • Rosso, Paolo|||0000-0002-8922-1242
  • Bosco, Cristina
  • Damiano, Rossana
  • Patti, Viviana
  • Cambria, Erik
[EN] Social and expressive media represent a challenge and a push forward for research on emotion and sentiment analysis. The advent of social media has brought about new paradigms of interaction that foster first-person engagement and crowdsourced contents: the subjective dimension moves to the foreground, opening the way to the emergence of an affective component within a dynamic corpus of digitized contents created and enriched by the users. Expressive media, which play a key role in fields related to creativity, such as figurative arts, music or drama, gather multimedia contents into online social environments, by joining the social dimension with the aims of artistic creation and self-expression. Artistic creation and performance seem to be a very interesting testbed for cross-validating and possibly integrating approaches, models and tools for automatically analyzing emotion and sentiment. In fact, in such contexts the social and affective dimensions (emotions and feelings) naturally emerge (Silvia, 2005), think for instance of the visitors’ feedback to a real or virtual art exhibition, or of the audience–performance interaction (...) In light of these considerations, this special issue focuses on the presentation and discussion of a set of novel computational approaches to the analysis of emotion and sentiment in social and expressive media., Paolo Rosso has been partially funded by the WIQ–EI IRSES project (Grant no. 269180) within the EC FP7 Marie Curie People Framework and by the DIANA-APPLICATIONS – Finding Hidden Knowledge in Texts: Applications project (TIN2012-38603-C02-01). The last phase of the work of Viviana Patti was carried out at the Universitat Politècnica de València in the framework of a three-month fellowship of the University of Turin within the World Wide Style (WWS) Program, Second Edition, co-funded by Fondazione CRT .
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Exploring high-level features for detecting cyberpedophilia

  • Bogdanova, Dasha
  • Solorio, Thamar
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] In this paper, we suggest a list of high-level features and study their applicability in detection of cyberpedophiles. We used a corpus of chats downloaded from http://www.perverted-justice.com and two negative datasets of different nature: cybersex logs available online, and the NPS chat corpus. The classification results show that the NPS data and the pedophiles’ conversations can be accurately discriminated from each other with character n-grams, while in the more complicated case of cybersex logs there is need for high-level features to reach good accuracy levels. In this latter setting our results show that features that model behaviour and emotion significantly outperform the low-level ones, and achieve a 97% accuracy., The work of Dasha Bogdanova was partially carried out during the internship at the Universitat Politecnica de Valencia (scholarship of the University of St. Petersburg). Her research was partially supported by Google Research Award. The collaboration with Thamar Solorio was possible thanks to her one-month research visit at the Universitat Politecnica de Valencia (program PAID-PAID-02-11 award n. 1932). The research work of Paolo Rosso was done in the framework of the European Commission WIQ-EI Web Information Quality Evaluation Initiative (IRSES Grant No. 269180) project within the FP 7 Marie Curie People, the DIANA-APPLICATIONS - Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-0O2-01) project, and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

A Systematic Study of Knowledge Graph Analysis for Cross-language Plagiarism Detection

  • Franco-Salvador, Marc
  • Montes Gomez, Manuel
  • Rosso, Paolo|||0000-0002-8922-1242
Cross-language plagiarism detection aims to detect plagiarised fragments of text among documents in different languages. In this paper, we perform a systematic examination of Cross-language Knowledge Graph Analysis; an approach that represents text fragments using knowledge graphs as a language independent content model. We analyse the contributions to cross-language plagiarism detection of the different aspects covered by knowledge graphs: word sense disambiguation, vocabulary expansion, and representation by similarities with a collection of concepts. In addition, we study both the relevance of concepts and their relations when detecting plagiarism. Finally, as a key component of the knowledge graph construction, we present a new weighting scheme of relations between concepts based on distributed representations of concepts. Experimental results in Spanish–English and German–English plagiarism detection show state-of-the-art performance and provide interesting insights on the use of knowledge graphs. © 2015 Elsevier Ltd. All rights reserved., This research has been carried out in the framework of the European Commission WIQ-EI IRSES (No. 269180) and DIANA APPLICATIONS - Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) projects. We would like to thank Tomas Mikolov, Martin Potthast, and Luis A. Leiva for their support and comments during this research.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

On the evaluation and improvement of arabic wordnet coverage and usability

  • Abouenour, Lahsen
  • Bouzoubaa, Karim
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] Built on the basis of the methods developed for Princeton WordNet and EuroWordNet, Arabic WordNet (AWN) has been an interesting project which combines WordNet structure compliance with Arabic particularities. In this paper, some AWN shortcomings related to coverage and usability are addressed. The use of AWN in question/answering (Q/A) helped us to deeply evaluate the resource from an experience-based perspective. Accordingly, an enrichment of AWN was built by semi-automatically extending its content. Indeed, existing approaches and/or resources developed for other languages were adapted and used for AWN. The experiments conducted in Arabic Q/A have shown an improvement of both AWN coverage as well as usability. Concerning coverage, a great amount of named entities extracted from YAGO were connected with corresponding AWN synsets. Also, a significant number of new verbs and nouns (including Broken Plural forms) were added. In terms of usability, thanks to the use of AWN, the performance for the AWN-based Q/A application registered an overall improvement with respect to the following three measures: accuracy (+9.27 % improvement), mean reciprocal rank (+3.6 improvement) and number of answered questions (+12.79 % improvement)., The work presented in Sect. 2.2 was done in the framework of the bilateral Spain-Morocco AECID-PCI C/026728/09 research project. The research of the two first authors is done in the framework of the PROGRAMME D'URGENCE project (grant no. 03/2010). The research of the third author is done in the framework of WIQEI IRSES project (grant no. 269180) within the FP 7 Marie Curie People, DIANA-APPLICATIONS-Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) research project and VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems. We would like to thank Manuel Montes-y-Gomez (INAOE-Puebla, Mexico) and Sandra Garcia-Blasco (Bitsnbrain, Spain) for their feedback on the work presented in Sect. 2.4. We would like finally to thank Violetta Cavalli-Sforza (Al Akhawayn University in Ifrane, Morocco) for having reviewed the linguistic level of the entire document.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Silhouette + Attraction: A Simple and Effective Method for Text Clustering

  • Errecalde, Marcelo
  • Cagnina, Leticia
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] This article presents silhouette attraction (Sil Att), a simple and effective method for text clustering, which is based on two main concepts: the silhouette coefficient and the idea of attraction. The combination of both principles allows us to obtain a general technique that can be used either as a boosting method, which improves results of other clustering algorithms, or as an independent clustering algorithm. The experimental work shows that Sil Att is able to obtain high-quality results on text corpora with very different characteristics. Furthermore, its stable performance on all the considered corpora is indicative that it is a very robust method. This is a very interesting positive aspect of Sil Att with respect to the other algorithms used in the experiments, whose performances heavily depend on specific characteristics of the corpora being considered., This research work has been partially funded by UNSL, CONICET (Argentina), DIANA-APPLICATIONS-Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) research project, and the WIQ-EI IRSES project (grant no. 269180) within the FP 7 Marie Curie People Framework on Web Information Quality Evaluation Initiative. The work of the third author was done also in the framework of the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Prototype/topic based Clustering Method for Weblogs

  • Perez-Tellez, Fernando
  • Cardiff, John
  • Pinto Avendaño, David Eduardo
  • Rosso, Paolo|||0000-0002-8922-1242
[EN] In the last 10 years, the information generated on weblog sites has increased exponentially, resulting in a clear need for intelligent approaches to analyse and organise this massive amount of information. In this work, we present a methodology to cluster weblog posts according to the topics discussed therein, which we derive by text analysis. We have called the methodology Prototype/Topic Based Clustering, an approach which is based on a generative probabilistic model in conjunction with a Self-Term Expansion methodology. The usage of the Self-Term Expansion methodology is to improve the representation of the data and the generative probabilistic model is employed to identify relevant topics discussed in the weblogs. We have modified the generative probabilistic model in order to exploit predefined initialisations of the model and have performed our experiments in narrow and wide domain subsets. The results of our approach have demonstrated a considerable improvement over the pre-defined baseline and alternative state of the art approaches, achieving an improvement of up to 20% in many cases. The experiments were performed on both narrow and wide domain datasets, with the latter showing better improvement. However in both cases, our results outperformed the baseline and state of the art algorithms., The work of the third author was carried out in the framework of the WIQ-EI IRSES project (Grant No. 269180) within the FP7 Marie Curie, the DIANA APPLICATIONS Finding Hidden Knowledge in Texts: Applications (TIN2012-38603-C02-01) project and the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.