Skip to main content

INRISCO: ANALISIS DE COMUNIDADES BASADO EN MINERIA SOCIAL

TEC2014-54335-C4-3-R

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2014
State Plan 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Management unit Secretaría de Estado de Educación, Formación Profesional y Universidades
Beneficiary centre UNIVERSIDAD DE VIGO

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Tesis doctoral (DoctoralThesis)

Applying data analysis to provide efficient and effective recommendation systems for e-commerce, Recomendaciones eficaces y eficientes para comercio electrónico basada en técnicas de análisis de datos, Recomendacións eficaces e eficientes para comercio eletrónico baseada en técnicas de análise de datos

  • Hafez, Manar Mohamed
Nowadays, the volume of information over the Internet is increasing at a tremendous rate. Therefore, the search for relevant and useful information is becoming difficult because the search engines on the Internet give hundreds to thousands of results on every query, while only a few of those results are relevant to the desired search. Specifically, in the e-commerce sector, the available products and the corresponding electronic information lead to the problem of information overload. Besides, online user's preferences are always changing, being adapted to the rapidly changes in the Web. That is why users take a lot of time to find the right information at the right time. Therefore, it is not uncommon that users feel frustrated after trying to search for information via Internet. Information overload refers to having too much information to make a decision about a product or topic. Therefore, this rapid growth of the Internet leads to information overload problem that appears in the form of the huge amount of online content including various types of products that can be purchased and sold. As a result, online shoppers will waste a lot of time in searching the suitable items or services they need, due to the existence of multiple kinds of items offered by e-commerce companies and the existence of a large number of online food websites. Nowadays, providing relevant product recommendations to customers plays an important role in retaining customers and improving their shopping experience. Recommender systems can be applied to industries such as an e-commerce, music, online radio, television, hospitality, finance and many more. Product recommender systems have become increasingly important, as consumers are exposed to massive amounts of product information on the Internet and product recommender systems can suggest alternative products that interest consumers. It has repeatedly proved that a simple algorithm using a huge amount of data should provide better results than a complex algorithm working over less data. Therefore, and as the recommendation system has to analyze the huge amount of data to provide better recommendations, it is considered as a data intensive application. Our research proposal will precisely focus on providing a supporting layer of algorithms (data analysis layer) that works with the information provided by the product producers, in especial, those products related to the food industry: ingredients, allergic information, health information, etc. This data will be used by the data analysis layer to relate products, to infer different useful information for consumers, to discover new categories, etc. Additionally, this layer will be able to identify useful information for specific groups of consumers, like athletes, people with diseases (such as diabetics, high levels of cholesterol, etc.) and people with food intolerance and/or allergies. Thus, the research expects the outcome to be helpful to online retailers in improving their online recommender systems., La búsqueda de información relevante y útil en Internet se revela una tarea compleja, dado el elevado volumen de información existente y la velocidad a la que sigue creciendo. Los actuales buscadores ofrecen cientos de miles de resultados en cada búsqueda, aunque sólo unos pocos son realmente relevantes. Este problema se agudiza en el sector del comercio electrónico, donde la sobrecarga de información es todavía mayor, con la descripción de productos disponibles y sus características. Así como la cantidad de información es cada vez mayor, las preferencias de los consumidores son también dinámicas, variando tan rápido como los propios cambios y la disponibilidad de productos en la Web. Esta conjunción provoca cierta frustración en el consumidor, que invierte demasiado tiempo en acceder a la información que le interesa, para después tomar la decisión de compra. Tampoco es conveniente para la propio sector del comercio electrónico, dado que proporcionar un entorno adecuado donde el cliente se sienta cómodo y donde pueda encontrar fácilmente lo que busca y/o encontrar productos alternativos ayuda a fidelizar a los usuarios y mejorar el rendimiento de las plataformas de venta. La propuesta de este trabajo pretende proporcionar una capa algorítmica (capa de análisis de datos) que funcione con la información facilitada por los proveedores de producto, en especial, aquellos productos relacionados con la industria alimentaria: ingredientes, información alérgica, información de salud, etc. Esta información será utilizada por la capa de análisis de datos para relacionar productos, inferir información útil diferente para los consumidores, descubrir nuevas categorías, etc. Además, esta capa podrá identificar información útil para grupos específicos de consumidores, como atletas, personas con enfermedades (como diabéticos, altos niveles de colesterol, etc.) y personas con intolerancia alimentaria y / o alergias. Adicionalmente, la capa algorítmica debe ser fácilmente parametrizable a diferentes sectores del comercio electrónico (no sólo la industria alimentaria), para poder adaptarse a diversos ámbitos de aplicación., A procura de información relevante e útil en Internet revélase unha tarefa complexa, dado o elevado volume de información existente e a velocidade á que segue crecendo. Os actuais buscadores ofrecen centos de miles de resultados en cada procura, aínda que só uns poucos son realmente relevantes. Este problema agudízase no sector do comercio electrónico, onde a sobrecarga de información é aínda maior, coa descrición de produtos dispoñibles e as súas características. Así como a cantidade de información é cada vez maior, as preferencias dos consumidores son tamén dinámicas, variando tan rápido como os propios cambios e a disponibilidad de produtos na Web. Esta conjunción provoca certa frustración no consumidor, que inviste demasiado tempo en acceder á información que lle interesa, para despois tomar a decisión de compra. Tampouco é conveniente para a propio sector do comercio electrónico, dado que proporcionar unha contorna adecuada onde o cliente séntase cómodo e onde poida atopar fácilmente o que busca e/ou atopar produtos alternativos axuda a fidelizar aos usuarios e mellorar o rendemento das plataformas de venda. A proposta deste traballo pretende proporcionar unha capa algorítmica (capa de análise de datos) que funcione coa información facilitada polos proveedores de produto, en especial, aqueles produtos relacionados coa industria alimentaria: ingredientes, información alérgica, información de saúde, etc. Esta información será utilizada pola capa de análise de datos para relacionar produtos, inferir información útil diferente para os consumidores, descubrir novas categorías, etc. Ademais, esta capa poderá identificar información útil para grupos específicos de consumidores, como atletas, persoas con enfermidades (como diabéticos, altos niveis de colesterol, etc.) e persoas con intolerancia alimentaria e / ou alergias. Adicionalmente, a capa algorítmica debe ser fácilmente parametrizable a diferentes sectores do comercio electrónico (non só a industria alimentaria), para poder adaptarse a diversos ámbitos de aplicación., Ministerio de Economía y Competitividad | Ref. TEC2014-84197-C4-2-R, Ministerio de Economía y Competitividad | Ref. TEC2014-54335-C4-3-R, Xunta de Galicia
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

The irruption of cryptocurrencies into twitter cashtags: a classifying solution

  • Fernández Vilas, Ana
  • Díaz Redondo, Rebeca Pilar
  • Lorenzo García, Antón
There is a consensus about the good sensing characteristics of Twitter to mine and uncover knowledge in financial markets, being considered a relevant feeder for taking decisions about buying or holding stock shares and even for detecting stock manipulation. Although Twitter hashtags allow to aggregate topic-related content, a specific mechanism for financial information also exists: Cashtag (consisting of the company ticker preceded by $) is a supporting mechanism to track financial tweets referring to a company listed in a stock market. However, according to our experiments and due to the lack of conventions in cashtags usage, the irruption of cryptocurrencies has resulted in a significant degradation on the cashtag-based aggregation of posts. Unfortunately, Twitter' users may use homonym tickers to refer to cryptocurrencies and to companies in stock markets, which means that filtering by cashtag may result on both posts referring to stock companies and cryptocurrencies. This research proposes automated classifiers to distinguish conflicting cashtags and, so, their container tweets by analyzing the distinctive features of tweets referring to stock companies and cryptocurrencies. As experiment, this paper analyses the interference between cryptocurrencies and company tickers in the London Stock Exchange (LSE), specifically, companies in the main and alternative market indices FTSE-100 and AIM-100. Heuristic-based as well as supervised classifiers are proposed and their advantages and drawbacks, including their ability to self-adapt to Twitter usage changes, are discussed. The experiment confirms a significant distortion in collected data when colliding or homonym cashtags exist, i.e., the same $ acronym to refer to company tickers and cryptocurrencies. According to our results, the distinctive features of posts including cryptocurrencies or company tickers support accurate classification of colliding tweets (homonym cashtags) and Independent Models, as the most detached classifiers from training data, have the potential to be trans-applicability (in different stock markets) while retaining performance., Ministerio de Economía y Competitividad | Ref. TEC2014-54335-C4-3-R, Agencia Estatal de Investigación | Ref. TEC2017-84197-C4-2-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

A hybrid analysis of LBSN data to early detect anomalies in crowd dynamics

  • Díaz Redondo, Rebeca Pilar
  • García Rubio, Carlos
  • Fernández Vilas, Ana
  • Campo Vázquez, María Celeste
  • Rodríguez Carrión, Alicia
Undoubtedly, Location-based Social Networks (LBSNs) provide an interesting source of geo-located data that we have previously used to obtain patterns of the dynamics of crowds throughout urban areas. According to our previous results, activity in LBSNs reflects the real activity in the city. Therefore, unexpected behaviors in the social media activity are a trustful evidence of unexpected changes of the activity in the city. In this paper we introduce a hybrid solution to early detect these changes based on applying a combination of two approaches, the use of entropy analysis and clustering techniques, on the data gathered from LBSNs. In particular, we have performed our experiments over a data set collected from Instagram for seven months in New York City, obtaining promising results., Ministerio de Economía y Competitividad | Ref. TEC2014-54335-C4-2-R, Ministerio de Economía y Competitividad | Ref. TEC2014-54335-C4-3-R, Agencia Estatal de Investigación | Ref. TEC2017-84197-C4-2-R, Agencia Estatal de Investigación | Ref. TEC2017-84197-C4-3-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Twitter permeability to financial events: an experiment towards a model for sensing irregularities

  • Fernández Vilas, Ana
  • Díaz Redondo, Rebeca Pilar
  • Crockett, Keeley
  • Owda, Majdi
  • Evans, Lewis
There is a general consensus of the good sensing and novelty characteristics of Twitter as an information media for the complex financial market. This paper investigates the permeability of Twittersphere, the total universe of Twitter users and their habits, towards relevant events in the financial market. Analysis shows that a general purpose social media is permeable to financial-specific events and establishes Twitter as a relevant feeder for taking decisions regarding the financial market and event fraudulent activities in that market. However, the provenance of contributions, their different levels of credibility and quality and even the purpose or intention behind them should to be considered and carefully contemplated if Twitter is used as a single source for decision taking. With the overall aim of this research, to deploy an architecture for real-time monitoring of irregularities in the financial market, this paper conducts a series of experiments on the level of permeability and the permeable features of Twitter in the event of one of these irregularities. To be precise, Twitter data is collected concerning an event comprising of a specific financial action on the 27th January 2017: the announcement about the merge of two companies Tesco PLC and Booker Group PLC, listed in the main market of the London Stock Exchange (LSE), to create the UK’s Leading Food Business. The experiment attempts to answer two research questions which aim to characterize the features of Twitter permeability to the financial market. The experimental results confirm that a far-impacting financial event, such as the merger considered, caused apparent disturbances in all the features considered, that is, information volume, content and sentiment as well as geographical provenance. Analysis shows that although Twitter is not a specific financial forum, it is permeable to financial events. Therefore it should be considered within the architecture for real-time monitoring of irregularities in the financial market., Ministerio de Economía y Competitividad | Ref. TEC2014-54335-C4-3-R, Agencia Estatal de Investigación | Ref. TEC2017-84197-C4-2-R