Product feature taxonomy learning based on user reviews

In recent years, the Web 2.0 has provided considerable facilities for people to create, share and exchange information and ideas. Upon this, the user generated content, such as reviews, has exploded. Such data provide a rich source to exploit in order to identify the information associated with specific reviewed items. Opinion mining has been widely used to identify the significant features of items (e.g., cameras) based upon user reviews. Feature extraction is the most critical step to identify useful information from texts. Most existing approaches only find individual features about a product without revealing the structural relationships between the features which usually exist. In this paper, we propose an approach to extract features and feature relationships, represented as a tree structure called feature taxonomy, based on frequent patterns and associations between patterns derived from user reviews. The generated feature taxonomy profiles the product at multiple levels and provides more detailed information about the product. Our experiment results based on some popularly used review datasets show that our proposed approach is able to capture the product features and relations effectively.

Structured feature extraction using association rules

As of today, opinion mining has been widely used to iden- tify the strength and weakness of products (e.g., cameras) or services (e.g., services in medical clinics or hospitals) based upon people's feed- back such as user reviews. Feature extraction is a crucial step for opinion mining which has been used to collect useful information from user reviews. Most existing approaches only find individual features of a product without the structural relationships between the features which usually exists. In this paper, we propose an approach to extract features and feature relationship, represented as tree structure called a feature hi- erarchy, based on frequent patterns and associations between patterns derived from user reviews. The generated feature hierarchy profiles the product at multiple levels and provides more detailed information about the product. Our experiment results based on some popularly used review datasets show that the proposed feature extraction approach can identify more correct features than the baseline model. Even though the datasets used in the experiment are about cameras, our work can be ap- plied to generate features about a service such as the services in hospitals or clinics.

A pilot study on affective classification of facial images for emerging news topics

The proliferation of news reports published in online websites and news information sharing among social media users necessitates effective techniques for analysing the image, text and video data related to news topics. This paper presents the first study to classify affective facial images on emerging news topics. The proposed system dynamically monitors and selects the current hot (of great interest) news topics with strong affective interestingness using textual keywords in news articles and social media discussions. Images from the selected hot topics are extracted and classified into three categorized emotions, positive, neutral and negative, based on facial expressions of subjects in the images. Performance evaluations on two facial image datasets collected from real-world resources demonstrate the applicability and effectiveness of the proposed system in affective classification of facial images in news reports. Facial expression shows high consistency with the affective textual content in news reports for positive emotion, while only low correlation has been observed for neutral and negative. The system can be directly used for applications, such as assisting editors in choosing photos with a proper affective semantic for a certain topic during news report preparation.

Asia Pacific Business Process Management

This book constitutes the proceedings of the Second Asia Pacific Conference on Business Process Management held in Brisbane, QLD, Australia, in July 2014. In all, 33 contributions from 12 countries were submitted. After each submission was reviewed by at least three Program Committee members, nine full papers were accepted for publication in this volume. These nine papers cover various topics that can be categorized under four main research focuses in BPM: process mining, process modeling and repositories, process model comparison, and process analysis.

Combining propensity and influence models for product adoption prediction

This paper studies the problem of selecting users in an online social network for targeted advertising so as to maximize the adoption of a given product. In previous work, two families of models have been considered to address this problem: direct targeting and network-based targeting. The former approach targets users with the highest propensity to adopt the product, while the latter approach targets users with the highest influence potential – that is users whose adoption is most likely to be followed by subsequent adoptions by peers. This paper proposes a hybrid approach that combines a notion of propensity and a notion of influence into a single utility function. We show that targeting a fixed number of high-utility users results in more adoptions than targeting either highly influential users or users with high propensity.

Generating product feature hierarchy from product reviews

User generated information such as product reviews have been booming due to the advent of web 2.0. In particular, rich information associated with reviewed products has been buried in such big data. In order to facilitate identifying useful information from product (e.g., cameras) reviews, opinion mining has been proposed and widely used in recent years. In detail, as the most critical step of opinion mining, feature extraction aims to extract significant product features from review texts. However, most existing approaches only find individual features rather than identifying the hierarchical relationships between the product features. In this paper, we propose an approach which finds both features and feature relationships, structured as a feature hierarchy which is referred to as feature taxonomy in the remainder of the paper. Specifically, by making use of frequent patterns and association rules, we construct the feature taxonomy to profile the product at multiple levels instead of single level, which provides more detailed information about the product. The experiment which has been conducted based upon some real world review datasets shows that our proposed method is capable of identifying product features and relations effectively.

Sistema para indexação e visualização de depoimentos de história oral: o caso do Museu da Pessoa

Esta dissertação apresenta a estruturação de um sistema para indexação e visualização de depoimentos de história oral em vídeo. A partir do levantamento de um referencial teórico referente à indexação, o sistema resultou em um protótipo funcional de alta fidelidade. O conteúdo para a realização deste foi obtido pela indexação de 12 depoimentos coletados pela equipe do Museu da Pessoa durante o projeto Memórias da Vila Madalena, em São Paulo (ago/2012). Acervos de História Oral como o Museu da Pessoa, o Museu da Imagem e do Som ou o Centro de Pesquisa e Documentação de História Contemporânea do Brasil / CPDOC da Fundação Getúlio Vargas, reúnem milhares de horas de depoimentos em áudio e vídeo. De uma forma geral, esses depoimentos são longas entrevistas individuais, onde diversos assuntos são abordados; o que dificulta sua análise, síntese e consequentemente, sua recuperação. A transcrição dos depoimentos permite a realização de buscas textuais para acessar assuntos específicos nas longas entrevistas. Por isso, podemos dizer que as transcrições são a principal fonte de consulta dos pesquisadores de história oral, deixando a fonte primária (o vídeo) para um eventual segundo momento da pesquisa. A presente proposta visa ampliar a recuperação das fontes primárias a partir da indexação de segmentos de vídeo, criando pontos de acesso imediato para trechos relevantes das entrevistas. Nessa abordagem, os indexadores (termos, tags ou anotações) não são associados ao vídeo completo, mas a pontos de entrada e saída (timecodes) que definem trechos específicos no vídeo. As tags combinadas com os timecodes criam novos desafios e possibilidades para indexação e navegação através de arquivos de vídeo. O sistema aqui estruturado integra conceitos e técnicas de áreas aparentemente desconectadas: metodologias de indexação, construção de taxonomias, folksonomias, visualização de dados e design de interação são integrados em um processo unificado que vai desde a coleta e indexação dos depoimentos até sua visualização e interação.

Rough sets, their extensions and applications

Q. Shen and R. Jensen, 'Rough sets, their extensions and applications,' International Journal of Automation and Computing (IJAC), vol. 4, no. 3, pp. 217-218, 2007.

Guest reputation indexes to analyze hotel’s online reputation using data extracted from OTAs

Nowadays many travelers use online travel agency (OTAs) to book flights, hotel rooms, rent-a-cars, cruises or entire vacation packages. Usually OTAs allow their users to give scores and to write reviews about what was used. Each OTA defines the terms and conditions for guest rating or review score and hoteliers are giving increasing importance to the scores and reviews their guests do in OTAs. This paper proposes two guest reputation index to help hoteliers to monitorize their presence in OTAs. The Aggregated Guest Reputation Index (AGRI), which shows the positioning of a hotel in different OTAs and it is calculated from the scores obtained by the hotels in those OTAs. Another one, the Semantic Guest Reputation Index (SGRI), which incorporates the social reputation of a hotel and that can be visualized through the development of word clouds or tag clouds. Examples of usage of these indexes are given with data extracted from 5-stars hotels in the Algarve, south region of Portugal, that are available on Booking and Expedia.

Apprentissage des réseaux de neurones profonds et applications en traitement automatique de la langue naturelle

En apprentissage automatique, domaine qui consiste à utiliser des données pour apprendre une solution aux problèmes que nous voulons confier à la machine, le modèle des Réseaux de Neurones Artificiels (ANN) est un outil précieux. Il a été inventé voilà maintenant près de soixante ans, et pourtant, il est encore de nos jours le sujet d'une recherche active. Récemment, avec l'apprentissage profond, il a en effet permis d'améliorer l'état de l'art dans de nombreux champs d'applications comme la vision par ordinateur, le traitement de la parole et le traitement des langues naturelles. La quantité toujours grandissante de données disponibles et les améliorations du matériel informatique ont permis de faciliter l'apprentissage de modèles à haute capacité comme les ANNs profonds. Cependant, des difficultés inhérentes à l'entraînement de tels modèles, comme les minima locaux, ont encore un impact important. L'apprentissage profond vise donc à trouver des solutions, en régularisant ou en facilitant l'optimisation. Le pré-entraînnement non-supervisé, ou la technique du ``Dropout'', en sont des exemples. Les deux premiers travaux présentés dans cette thèse suivent cette ligne de recherche. Le premier étudie les problèmes de gradients diminuants/explosants dans les architectures profondes. Il montre que des choix simples, comme la fonction d'activation ou l'initialisation des poids du réseaux, ont une grande influence. Nous proposons l'initialisation normalisée pour faciliter l'apprentissage. Le second se focalise sur le choix de la fonction d'activation et présente le rectifieur, ou unité rectificatrice linéaire. Cette étude a été la première à mettre l'accent sur les fonctions d'activations linéaires par morceaux pour les réseaux de neurones profonds en apprentissage supervisé. Aujourd'hui, ce type de fonction d'activation est une composante essentielle des réseaux de neurones profonds. Les deux derniers travaux présentés se concentrent sur les applications des ANNs en traitement des langues naturelles. Le premier aborde le sujet de l'adaptation de domaine pour l'analyse de sentiment, en utilisant des Auto-Encodeurs Débruitants. Celui-ci est encore l'état de l'art de nos jours. Le second traite de l'apprentissage de données multi-relationnelles avec un modèle à base d'énergie, pouvant être utilisé pour la tâche de désambiguation de sens.

Web Science and Data Analytics Course

Resources from the Singapore Summer School 2014 hosted by NUS. ws-summerschool.comp.nus.edu.sg

What can Flickr photographs tell us about the world?

In their second year, our undergraduate web scientists undertake a group project module (WEBS2002, led by Jonathon Hare & co-taught by Su White) in which they get to apply what they learnt in the first year to a practical web-science problem, and also learn about team-working. For the project this semester, the students were provided with a large dataset of geolocated images and associated metadata collected from the Flickr website. Using this data, they were tasked with exploring what this data could tell us about the world. In this seminar the two groups will present the outcomes of their work. Team Alpha (Ellie Hamilton, Clayton Jones & Alok Acharya) will present their work on "The relationship between Group Photos, Social Integration and Suicide". This work aims to explore whether levels of social integration (which Durkheim posited as a factor in "Egoistic Suicide" rates) can be predicted by measuring the proportion of photos of groups of people to photos of individuals within a geographical region. Team Bravo (Agnieszka Grzesiuk-Szolucha, Thomas Leese & Ammaar Tawil) will present their work on "Sentiment Analysis on Flickr Photo Tags to Classify a Photo as Positive or Negative, In Order to Determine the Happiness of a Country or Region". This work explores whether estimates of sentiment made by applying SentiWordNet to Flickr tags correlate with indices of world happiness and socio-economic well-being.

Optimización del sistema de transporte en el colegio The English School

La optimización de sistemas y modelos se ha convertido en uno de los factores más importantes a la hora de buscar la mayor eficiencia de un proceso. Este concepto no es ajeno al transporte escolar, ambiente que cambia constantemente al ritmo de las necesidades de sus clientes, y que responde ante una fuerte responsabilidad frente a sus usuarios, los niños que hacen uso del servicio, en cuanto al cumplimiento de tiempos y seguridad, mientras busca constantemente la reducción de costos. Este proyecto expone las problemáticas presentadas en The English School en esta área y propone un modelo de optimización simple que permitirá notables mejoras en términos de tiempos y costos, de tal forma que genere beneficios para la institución en términos financieros y de satisfacción al cliente. Por medio de la implementación de este modelo será posible identificar errores comunes del proceso, se identificarán soluciones prácticas de fácil aplicación en el manejo del transporte y se presentarán los resultados obtenidos en la muestra utilizada para desarrollar el proyecto.

Newly Automated System For Integrated Assessment Of The Conditions Of Underwater Gas Pipelines

An underwater gas pipeline is the portion of the pipeline that crosses a river beneath its bottom. Underwater gas pipelines are subject to increasing dangers as time goes by. An accident at an underwater gas pipeline can lead to technological and environmental disaster on the scale of an entire region. Therefore, timely troubleshooting of all underwater gas pipelines in order to prevent any potential accidents will remain a pressing task for the industry. The most important aspect of resolving this challenge is the quality of the automated system in question. Now the industry doesn't have any automated system that fully meets the needs of the experts working in the field maintaining underwater gas pipelines. Principle Aim of this Research: This work aims to develop a new system of automated monitoring which would simplify the process of evaluating the technical condition and decision making on planning and preventive maintenance and repair work on the underwater gas pipeline. Objectives: Creation a shared model for a new, automated system via IDEF3; Development of a new database system which would store all information about underwater gas pipelines; Development a new application that works with database servers, and provides an explanation of the results obtained from the server; Calculation of the values MTBF for specified pipelines based on quantitative data obtained from tests of this system. Conclusion: The new, automated system PodvodGazExpert has been developed for timely and qualitative determination of the physical conditions of underwater gas pipeline; The basis of the mathematical analysis of this new, automated system uses principal component analysis method; The process of determining the physical condition of an underwater gas pipeline with this new, automated system increases the MTBF by a factor of 8.18 above the existing system used today in the industry.

Política de desenvolvimento e o setor de mineração: análise de discursos do governo do Peru no período de 1990 a 2009

Os estudos sobre desenvolvimento, sem dúvida, se mantiveram como um dos últimos bastiões do modernismo nas ciências sociais (Rapley, 2004). Muitos dos dilemas chave em estudos contemporâneos sobre desenvolvimento se centraram nas disjuntivas entre inovação teórica, política e prática (Simon, 2003). No entanto, a discussão que envolve a relação entre desenvolvimento e mineração, que interessa neste estudo, ainda permanece acrítica dentro da literatura dominante. Segundo Graulau (2008), o tema de mineração encontra-se num vaivém entre o favoritismo e a oposição. O estudo sob o ponto de vista normativo da mineração no campo de desenvolvimento mostra a mentalidade econômica de longa data que prevalece nesse campo. No Peru as reformas neoliberais implantadas desde a década 1990 têm promovido fortemente o setor de mineração. Os investimentos nacionais e estrangeiros, o volume das exportações e impostos certamente têm influenciado favoravelmente na economia em termos macroeconômicos, obtendo quantidades consideráveis de divisas (UNCTAD, 2008). Não obstante, a grande mineração parece não ter beneficiado as comunidades envolvidas com a extração de minérios (Barrantes, 2005; Glave e Kuramoto, 2007; Zegarra; Orihuela e Paredes, 2007). A quantidade e gravidade dos conflitos que vem acontecendo evidenciam a resistência ao setor, frente à ação discursiva do Estado peruano sobre o “desenvolvimento” que assegura o que a mineração traz. Neste contexto este estudo tem como objetivo analisar as práticas discursivas das políticas de mineração peruana em relação a construção do discurso de desenvolvimento no período compreendido entre 1990-2009. Com esse objetivo, foi necessário abordar primeiramente as principais teorias sobre desenvolvimento, mineração e mineração no Peru. No que diz respeito à metodologia o presente estudo utilizou duas técnicas de análise: a Análise Crítica de Discurso, baseado no método tridimensional proposto por Fairclough (2001), para realizar a análise de três discursos de representantes da política de mineração peruana, a segunda abordagem utiliza a Análise de Conteúdo de Bardin (2009), para examinar os artigos relacionados à política de mineração entre as principais revistas especializadas do setor–Mineria e Desde Adentro. Foram utilizadas também categorias de análise constantes e convergentes ao conceito de desenvolvimento para orientar a presente pesquisa. Finalmente as conclusões sugerem que as políticas de mineração reproduzidas pelas autoridades do Estado peruano introduziram práticas discursivas sobre desenvolvimento sustentável e que essas se mantêm relacionadas com as novas ordens de discurso: Responsabilidade Social, Minerção Sustentável, Mineração moderna, Gestão ambiental.