Ingeniero Civil Industrial / En la siguiente memoria se busca corroborar, por medio de una experiencia práctica y aplicada, si a caso el uso de las técnicas de Web Opinion Mining (WOM) y de herramientas informáticas, permiten determinar las tendencias generales que pueden poseer un conjunto de opiniones presentes en la Web. Particularmente, los reclamos publicados en el sitio web Reclamos.cl, y que apuntan contra instituciones pertenecientes a las industrias nacionales de Educación y de Gobierno. En ese sentido, los consumidores cada vez están utilizando más la Web para publicar en ella las apreciaciones positivas y negativas que poseen sobre lo que adquieren en el mercado, situación que hace de esta una mina de oro para diversas instituciones, especialmente para lo que es el identificar las fortalezas y las debilidades de los productos y los servicios que ofrecen, su imagen pública, entre varios otros aspectos. Concretamente, el experimento se realiza a través de la confección y la ejecución de una aplicación informática que integra e implementa conceptos de WOM, tales como Knowledge Discovery from Data (KDD), a modo de marco metodológico para alcanzar el objetivo planteado, y Latent Dirichlet Allocation (LDA), para lo que es la detección de tópicos dentro de los contenidos de los reclamos abordados. También se hace uso de programación orientada a objetos, basada en el lenguaje Python, almacenamiento de datos en bases de datos relacionales, y se incorporan herramientas pre fabricadas con tal de simplificar la realización de ciertas tareas requeridas. La ejecución de la aplicación permitió descargar las páginas web en cuyo interior se encontraban los reclamos de interés para la realización experimento, detectando en ellas 6.460 de estos reclamos; los cueles estaban dirigidos hacia 245 instituciones, y cuya fecha de publicación fue entre el 13 de Julio de 2006 y el 5 de Diciembre de 2011. Así también, la aplicación, mediante el uso de listas de palabras a descartar y de herramientas de lematización, procesó los contenidos de los reclamos, dejando en ellos sólo las versiones canónicas de las palabras que los constituían y que aportasen significado a estos. Con ello, la aplicación llevó a cabo varios análisis LDA sobre estos contenidos, los que arbitrariamente se definieron para ser ejecutados por cada institución detectada, tanto sobre el conjunto total de sus reclamos, como en segmentos de estos agrupados por año de publicación, con tal de generar, por cada uno de estos análisis, resultados compuestos por 20 tópicos de 30 palabras cada uno. Con los resultados de los análisis LDA, y mediante una metodología de lectura e interpretación manual de las palabras que constituían cada uno de los conjuntos de tópicos obtenidos, se procedió a generar frases y oraciones que apuntasen a hilarlas, con tal de obtener una interpretación que reflejase la tendencia a la cual los reclamos, representados en estos resultados, apuntaban. De esto se pudo concluir que es posible detectar las tendencias generales de los reclamos mediante el uso de las técnicas de WOM, pero con observaciones al respecto, pues al surgir la determinación de las tendencias desde un proceso de interpretación manual, se pueden generar subjetividades en torno al objeto al que apuntan dichas tendencias, ya sea por los intereses, las experiencias, entre otros, que posea la persona que realice el ejercicio de interpretación de los resultados.

Cette thèse s’intéresse à l’adaptation d’un classifieur statistique d’opinion au niveau du texte d’un domaine à un autre. Cependant, nous exprimons notre opinion différemment selon ce dont nous parlons. Un même mot peut ne pas désigner pas la même chose ou bien ne pas avoir la même connotation selon le thème de la discussion. Si ces mots ne sont pas détectés, ils induiront des erreurs de classification.Nous appelons donc marqueurs multi-polaires des mots ou bigrammes dont la présence indique une certaine polarité du texte entier, différente selon le domaine du texte. Cette thèse est consacrées à leur étude. Ces marqueurs sont détectés à l’aide d’un test du khi2 lorsque l’on dispose d’annotations au niveau du texte dans les deux domaines d’intérêt. Nous avons également proposé une méthode de détection semi-supervisé. Nous utilisons une collections de mots pivots auto-épurés afin d’assurer une polarité stable d’un domaine à un autre.Nous avons également vérifié la pertinence linguistique des mots sélectionnés en organisant une campagne d’annotation manuelle. Les mots ainsi validés comme multi-polaires peuvent être des éléments de contexte, des mots exprimant ou expliquant une opinion ou bien désignant l’objet sur lequel l’opinion est portée. Notre étude en contexte a également mis en lumière trois causes principale de changement de polarité : le changement de sens, le changement d’objet et le changement d’utilisation.Pour finir, nous avons étudié l’influence de la détection des marqueurs multi-polaires sur la classification de l’opinion au niveau du texte par des classifieurs automatiques dans trois cas distincts : adaptation d’un domaine source à un domaine cible, corpus multi-domaine, corpus en domaine ouvert. Les résultats de ces expériences montrent que plus le transfert initial est difficile, plus la prise en compte des marqueurs multi-polaires peut améliorer la classification, allant jusqu’à plus cinq points d’exactitude. / In this thesis, we are studying the adaptation of a text level opinion classifier across domains. Howerver, people express their opinion in a different way depending on the subject of the conversation. The same word in two different domains can refer to different objects or have an other connotation. If these words are not detected, they will lead to classification errors.We call these words or bigrams « multi-polarity marquers ». Their presence in a text signals a polarity wich is different according to the domain of the text. Their study is the subject of this thesis. These marquers are detected using a khi2 test if labels exist in both targeted domains. We also propose a semi-supervised detection method for the case with labels in only one domain. We use a collection of auto-epurated pivot words in order to assure a stable polarity accross domains.We have also checked the linguistic interest of the selected words with a manual evaluation campaign. The validated words can be : a word of context, a word giving an opinion, a word explaining an opinion or a word wich refer to the evaluated object. Our study also show that the causes of the changing polarity are of three kinds : changing meaning, changing object or changing use.Finally, we have studyed the influence of multi-polarity marquers on opinion classification at text level in three different cases : adaptation of a source domain to a target domain, multi-domain corpora and open domain corpora. The results of our experiments show that the potential improvement is bigger when the initial transfer was difficult. In the favorable cases, we improve accurracy up to five points.

Aspect-based sentiment analysis is the field of study which extracts and interpret the sentiment, usually classified as positive or negative, towards some target or aspect in an opinionated text. This doctoral dissertation details an empirical study of techniques and methods for aspect extraction in aspect-based sentiment analysis with the focus on Portuguese. Three different approaches were explored: frequency-based, relation-based and machine learning. In each one, this work shows a comparative study between a Portuguese and an English corpora and the differences found in applying the approaches. In addition, richer linguistic knowledge is also explored by using syntatic dependencies and semantic roles, leading to better results. This work lead to the establishment of new benchmarks for the aspect extraction in Portuguese. / A análise do sentimento orientada a aspectos é o campo de estudo que extrai e interpreta o sentimento, geralmente classificado como positivo ou negativo, em direção a algum alvo ou aspecto em um texto de opinião. Esta tese de doutorado detalha um estudo empírico de técnicas e métodos para extração de aspectos em análises de sentimentos baseadas em aspectos com foco na língua Portuguesa. Foram exploradas três diferentes abordagens: métodos baseados na frequências, métodos baseados na relação e métodos de aprendizagem de máquina. Em cada abordagem, este trabalho mostra um estudo comparativo entre um córpus para o Português e outro para o Inglês e as diferenças encontradas na aplicação destas abordagens. Além disso, o conhecimento linguístico mais rico também é explorado pelo uso de dependências sintáticas e papéis semânticos, levando a melhores resultados. Este trabalho resultou no estabelecimento de novos padrões de avaliação para a extração de aspectos em Português.

The task of opinion mining from product reviews has been achieved by employing rule-based approaches or generative learning models such as hidden Markov models (HMMs). This paper introduced a discriminative model using linear-chain Conditional Random Fields (CRFs) that can naturally incorporate arbitrary, non-independent features of the input without conditional independence among the features or distributional assumptions of inputs. The framework firstly performs part-of-speech (POS) tagging tasks over each word in sentences of review text. The performance is evaluated based on three criteria: precision, recall and F-score. The result shows that this approach is effective for this type of natural language processing (NLP) tasks. Then the framework extracts the keywords associated with each product feature and summarizes into concise lists that are simple and intuitive for people to read.

Les définitions des mots « sentiment », « opinion » et « émotion » sont toujours très vagues comme l’atteste aussi le dictionnaire qui semble expliquer un mot en utilisant le deux autres. Tout le monde est affecté par les opinions : les entreprises pour vendre les produits, les gens pour les acheter et, plus en général, pour prendre des décisions, les chercheurs en intelligence artificielle pour comprendre la nature de l’être humain. Aujourd’hui on a une quantité d’information disponible jamais vue avant, mais qui résulte peu accessible. Les mégadonnées (en anglais « big data ») ne sont pas organisées, surtout pour certaines langues – dont la difficulté à les exploiter. La recherche française souffre d’une manque de ressources « prêt-à-porter » pour conduire des tests. Cette thèse a l’objectif d’explorer la nature des sentiments et des émotions, dans le cadre du Traitement Automatique du Langage et des Corpus. Les contributions de cette thèse sont plusieurs : création de nouvelles ressources pour l’analyse du sentiment et de l’émotion, emploi et comparaison de plusieurs techniques d’apprentissage automatique, et plus important, l’étude du problème sous différents points de vue : classification des commentaires en ligne en polarité (positive et négative), Aspect-Based Sentiment Analysis des caractéristiques du produit recensé. Enfin, un étude psycholinguistique, supporté par des approches lexicales et d’apprentissage automatique, sur le rapport entre qui juge et l’objet jugé. / "Sentiment", "opinion" and "emotion" are words really vaguely defined; not even the dictionary seems to be of any help, being it the first to define each of the three by using the remaining two. And yet, the civilised world is heavily affected by opinions: companies need them to understand how to sell their products; people use them to buy the most fitting product and, more generally, to weigh their decisions; researchers exploit them in Artificial Intelligence studies to understand the nature of the human being. Today we can count on a humongous amount of available information, though it’s hard to use it. In fact, the so-called “Big data” are not always structured – especially for certain languages. French research suffers from a lack of readily available resources for tests. In the context of Natural Language Processing, this thesis aims to explore the nature of sentiment and emotion. Some of our contributions to the NLP research community are: creation of new resources for sentiment and emotion analysis, tests and comparisons of several machine learning methods to study the problem from different points of view - classification of online reviews using sentiment polarity, classification of product characteristics using Aspect- Based Sentiment Analysis. Finally, a psycholinguistic study - supported by a machine learning and lexical approaches – on the relation between who judges, the reviewer, and the object that has been judged, the product.

In today’s world, it is not enough for companies to consider any one social media channel in isolation. Instead, they must provide their customers with a unified experience across channels and consider interdependencies between channels. Most marketing research that examines user generated content is focused on a single channel and is limited to the English language. This thesis analyses Swedish language content collected from eight different social media platforms: Facebook, YouTube, Instagram, TikTok, Twitter, Tripadvisor, Trustpilot, and Google Reviews. The platforms were compared pairwise by the prevalence of positive, negative, and neutral sentiment in comments and reviews about the theme park Liseberg. The sentiment was predicted using a lexical approach where each word in a wordlist was assigned a weight to denote positive or negative sentiment associated with the word. The study found that there is a statistically significant difference between the positivity, negativity, and neutrality expressed by users on the different social media channels. There was no difference in sentiment between YouTube and Instagram comments, but there were differences in at least one of the three sentiment categories for all other pairwise comparisons of platforms. Having an understanding of the attitudes towards the brand in different channels can support marketers in determining their optimal mix of social media channels. These results are also of interest to researchers who should take the differences between social media platforms into consideration when designing studies around user generated content.

Opinion Mining is becoming the fastest growing area to extract useful and insightful information to support decision making. In the age of social media, user’s opinions and discussions have become a highly valuable source to look for users preferences, likes, and dislikes. The industry of wildlife parks (or zoos) is a competitive domain that requires careful analysis of visitor’s opinions to understand and cater for their preferences when it comes to wildlife. In this thesis, an opinion mining approach was proposed and applied on textual posts on the social media platform, Twitter, to extract the popularity, polarity (sentiment), and emotions toward birds and bird types such as owls, sparrows, etc. Then, the thesis provides recommendations based on popularity of birds and bird types and a ranked list of the most desired birds based on consumer emotions toward them. The findings of this thesis can help wildlife parks in the decision-making process on the types of birds to acquire.

No description available.

Product defects concern various groups of people, such as customers, manufacturers, government officials, etc. Thus, defect-related knowledge and information are essential. In keeping with the growth of social media, online forums, and Internet commerce, people post a vast amount of feedback on products, which forms a good source for the automatic acquisition of knowledge about defects. However, considering the vast volume of online reviews, how to automatically identify critical product defects and summarize the related information from the huge number of user reviews is challenging, even when we target only the negative reviews. As a kind of opinion mining research, existing defect discovery methods mainly focus on how to classify the type of product issues, which is not enough for users. People expect to see defect information in multiple facets, such as product model, component, and symptom, which are necessary to understand the defects and quantify their influence. In addition, people are eager to seek problem resolutions once they spot defects. These challenges cannot be solved by existing aspect-oriented opinion mining models, which seldom consider the defect entities mentioned above. Furthermore, users also want to better capture the semantics of review text, and to summarize product defects more accurately in the form of natural language sentences. However, existing text summarization models including neural networks can hardly generalize to user review summarization due to the lack of labeled data. In this research, we explore topic models and neural network models for product defect discovery and summarization from user reviews. Firstly, a generative Probabilistic Defect Model (PDM) is proposed, which models the generation process of user reviews from key defect entities including product Model, Component, Symptom, and Incident Date. Using the joint topics in these aspects, which are produced by PDM, people can discover defects which are represented by those entities. Secondly, we devise a Product Defect Latent Dirichlet Allocation (PDLDA) model, which describes how negative reviews are generated from defect elements like Component, Symptom, and Resolution. The interdependency between these entities is modeled by PDLDA as well. PDLDA answers not only what the defects look like, but also how to address them using the crowd wisdom hidden in user reviews. Finally, the problem of how to summarize user reviews more accurately, and better capture the semantics in them, is studied using deep neural networks, especially Hierarchical Encoder-Decoder Models. For each of the research topics, comprehensive evaluations are conducted to justify the effectiveness and accuracy of the proposed models, on heterogeneous datasets. Further, on the theoretical side, this research contributes to the research stream on product defect discovery, opinion mining, probabilistic graphical models, and deep neural network models. Regarding impact, these techniques will benefit related users such as customers, manufacturers, and government officials. / Ph. D. / Product defects concern various groups of people, such as customers, manufacturers, and government officials. Thus, defect-related knowledge and information are essential. In keeping with the growth of social media, online forums, and Internet commerce, people post a vast amount of feedback on products, which forms a good source for the automatic acquisition of knowledge about defects. However, considering the vast volume of online reviews, how to automatically identify critical product defects and summarize the related information from the huge number of user reviews is challenging, even when we target only the negative reviews. People expect to see defect information in multiple facets, such as product model, component, and symptom, which are necessary to understand the defects and quantify their influence. In addition, people are eager to seek problem resolutions once they spot defects. Furthermore, users also want to better summarize product defects more accurately in the form of natural language sentences. These requirements cannot be satisfied by existing methods, which seldom consider the defect entities mentioned above, or hardly generalize to user review summarization. In this research, we develop novel Machine Learning (ML) algorithms for product defect discovery and summarization. Firstly, we study how to identify product defects and their related attributes, such as Product Model, Component, Symptom, and Incident Date. Secondly, we devise a novel algorithm, which can discover product defects and the related Component, Symptom, and Resolution, from online user reviews. This method tells not only what the defects look like, but also how to address them using the crowd wisdom hidden in user reviews. Finally, we address the problem of how to summarize user reviews in the form of natural language sentences using a paraphrase-style method. On the theoretical side, this research contributes to multiple research areas in Natural Language Processing (NLP), Information Retrieval (IR), and Machine Learning. Regarding impact, these techniques will benefit related users such as customers, manufacturers, and government officials.

Im Social Commerce entwickeln sich die Kunden zu einer bedeutenden Informationsquelle für Unternehmen. Die Kunden nutzen die Kommunikationsplattformen des Web 2.0 (z.B. Twitter), um ihre Meinungen und Erfahrungen über Produkte zu äußern. Diese Diskussionen können sehr wichtig für die Entwicklung von Produkten eines Unternehmens sein. Ein modellbasierter Ansatz soll es einem Unternehmen ermöglichen, die Meinungen zu seinen Produkten in Microblogs zu betrachten. Der erste Schritt dafür ist die Erkennung von Themen in einem spezifischen Kontext. In einem weiteren Schritt müssen die zu den Themen korrespondierenden Einträge bezüglich der geäußerten Meinungen analysiert werden. Für die Erkennung der Themen kommt ein Verfahren zum Einsatz, das auf der Latent Dirichlet Allocation basiert. Das Verfahren identifizierte eventbasierte Themen im Zusammenhang mit den 3D-TV-Anlagen von Sony.