Learning user and product distributed representations using a sequence model for sentiment analysis

In product reviews, it is observed that the distribution of polarity ratings over reviews written by different users or evaluated based on different products are often skewed in the real world. As such, incorporating user and product information would be helpful for the task of sentiment classification of reviews. However, existing approaches ignored the temporal nature of reviews posted by the same user or evaluated on the same product. We argue that the temporal relations of reviews might be potentially useful for learning user and product embedding and thus propose employing a sequence model to embed these temporal relations into user and product representations so as to improve the performance of document-level sentiment analysis. Specifically, we first learn a distributed representation of each review by a one-dimensional convolutional neural network. Then, taking these representations as pretrained vectors, we use a recurrent neural network with gated recurrent units to learn distributed representations of users and products. Finally, we feed the user, product and review representations into a machine learning classifier for sentiment classification. Our approach has been evaluated on three large-scale review datasets from the IMDB and Yelp. Experimental results show that: (1) sequence modeling for the purposes of distributed user and product representation learning can improve the performance of document-level sentiment classification; (2) the proposed approach achieves state-of-The-Art results on these benchmark datasets.

Research on the influence of behavioral forces that motivate trader behavior and sentiment: A prospect theory exegesis

This study focuses on empirical investigations and seeks implications by utilizing three different methodologies to test various aspects of trader behavior. The first methodology utilizes Prospect Theory to determine trader behavior during periods of extreme wealth contracting periods. Secondly, a threshold model to examine the sentiment variable is formulated and thirdly a study is made of the contagion effect and trader behavior. ^ The connection between consumers' sense of financial well-being or sentiment and stock market performance has been studied at length. However, without data on actual versus experimental performance, implications based on this relationship are meaningless. The empirical agenda included examining a proprietary file of daily trader activities over a five-year period. Overall, during periods of extreme wealth altering conditions, traders "satisfice" rather than choose the "best" alternative. A trader's degree of loss aversion depends on his/her prior investment performance. A model that explains the behavior of traders during periods of turmoil is developed. Prospect Theory and the data file influenced the design of the model. ^ Additional research included testing a model that permitted the data to signal the crisis through a threshold model. The third empirical study sought to investigate the existence of contagion caused by declining global wealth effects using evidence from the mining industry in Canada. Contagion, where a financial crisis begins locally and subsequently spreads elsewhere, has been studied in terms of correlations among similar regions. The results provide support for Prospect Theory in two out of the three empirical studies. ^ The dissertation emphasizes the need for specifying precise, testable models of investors' expectations by providing tools to identify paradoxical behavior patterns. True enhancements in this field must include empirical research utilizing reliable data sources to mitigate data mining problems and allow researchers to distinguish between expectations-based and risk-based explanations of behavior. Through this type of research, it may be possible to systematically exploit "irrational" market behavior. ^

Essays on the impact of stakeholders' sentiment on the financial decision making process

The most important factor that affects the decision making process in finance is the risk which is usually measured by variance (total risk) or systematic risk (beta). Since investors’ sentiment (whether she is an optimist or pessimist) plays a very important role in the choice of beta measure, any decision made for the same asset within the same time horizon will be different for different individuals. In other words, there will neither be homogeneity of beliefs nor the rational expectation prevalent in the market due to behavioral traits. This dissertation consists of three essays. In the first essay, “ Investor Sentiment and Intrinsic Stock Prices”, a new technical trading strategy was developed using a firm specific individual sentiment measure. This behavioral based trading strategy forecasts a range within which a stock price moves in a particular period and can be used for stock trading. Results indicate that sample firms trade within a range and give signals as to when to buy or sell. In the second essay, “Managerial Sentiment and the Value of the Firm”, examined the effect of managerial sentiment on the project selection process using net present value criterion and also effect of managerial sentiment on the value of firm. Final analysis reported that high sentiment and low sentiment managers obtain different values for the same firm before and after the acceptance of a project. Changes in the cost of capital, weighted cost of average capital were found due to managerial sentiment. In the last essay, “Investor Sentiment and Optimal Portfolio Selection”, analyzed how the investor sentiment affects the nature and composition of the optimal portfolio as well as the portfolio performance. Results suggested that the choice of the investor sentiment completely changes the portfolio composition, i.e., the high sentiment investor will have a completely different choice of assets in the portfolio in comparison with the low sentiment investor. The results indicated the practical application of behavioral model based technical indicator for stock trading. Additional insights developed include the valuation of firms with a behavioral component and the importance of distinguishing portfolio performance based on sentiment factors.

Essays on the Impact of Stakeholders' Sentiment on the Financial Decision Making Process

The most important factor that affects the decision making process in finance is the risk which is usually measured by variance (total risk) or systematic risk (beta). Since investors' sentiment (whether she is an optimist or pessimist) plays a very important role in the choice of beta measure, any decision made for the same asset within the same time horizon will be different for different individuals. In other words, there will neither be homogeneity of beliefs nor the rational expectation prevalent in the market due to behavioral traits. This dissertation consists of three essays. In the first essay, Investor Sentiment and Intrinsic Stock Prices, a new technical trading strategy is developed using a firm specific individual sentiment measure. This behavioral based trading strategy forecasts a range within which a stock price moves in a particular period and can be used for stock trading. Results show that sample firms trade within a range and show signals as to when to buy or sell. The second essay, Managerial Sentiment and the Value of the Firm, examines the effect of managerial sentiment on the project selection process using net present value criterion and also effect of managerial sentiment on the value of firm. Findings show that high sentiment and low sentiment managers obtain different values for the same firm before and after the acceptance of a project. The last essay, Investor Sentiment and Optimal Portfolio Selection, analyzes how the investor sentiment affects the nature and composition of the optimal portfolio as well as the performance measures. Results suggest that the choice of the investor sentiment completely changes the portfolio composition, i.e., the high sentiment investor will have a completely different choice of assets in the portfolio in comparison with the low sentiment investor. The results indicate the practical application of behavioral model based technical indicators for stock trading. Additional insights developed include the valuation of firms with a behavioral component and the importance of distinguishing portfolio performance based on sentiment factors.

Research on the influence of behavioral forces that motivate trader behavior and sentiment- a prospect theory exegesis

This study focuses on empirical investigations and seeks implications by utilizing three different methodologies to test various aspects of trader behavior. The first methodology utilizes Prospect Theory to determine trader behavior during periods of extreme wealth contracting periods. Secondly, a threshold model to examine the sentiment variable is formulated and thirdly a study is made of the contagion effect and trader behavior. The connection between consumers' sense of financial well-being or sentiment and stock market performance has been studied at length. However, without data on actual versus experimental performance, implications based on this relationship are meaningless. The empirical agenda included examining a proprietary file of daily trader activities over a five-year period. Overall, during periods of extreme wealth altering conditions, traders "satisfice" rather than choose the "best" alternative. A trader's degree of loss aversion depends on his/her prior investment performance. A model that explains the behavior of traders during periods of turmoil is developed. Prospect Theory and the data file influenced the design of the model. Additional research included testing a model that permitted the data to signal the crisis through a threshold model. The third empirical study sought to investigate the existence of contagion caused by declining global wealth effects using evidence from the mining industry in Canada. Contagion, where a financial crisis begins locally and subsequently spreads elsewhere, has been studied in terms of correlations among similar regions. The results provide support for Prospect Theory in two out of the three empirical studies. The dissertation emphasizes the need for specifying precise, testable models of investors' expectations by providing tools to identify paradoxical behavior patterns. True enhancements in this field must include empirical research utilizing reliable data sources to mitigate data mining problems and allow researchers to distinguish between expectations-based and risk-based explanations of behavior. Through this type of research, it may be possible to systematically exploit "irrational" market behavior.

Text analytics of social media: Sentiment analysis, event detection and summarization

In the last decade, large numbers of social media services have emerged and been widely used in people's daily life as important information sharing and acquisition tools. With a substantial amount of user-contributed text data on social media, it becomes a necessity to develop methods and tools for text analysis for this emerging data, in order to better utilize it to deliver meaningful information to users. ^ Previous work on text analytics in last several decades is mainly focused on traditional types of text like emails, news and academic literatures, and several critical issues to text data on social media have not been well explored: 1) how to detect sentiment from text on social media; 2) how to make use of social media's real-time nature; 3) how to address information overload for flexible information needs. ^ In this dissertation, we focus on these three problems. First, to detect sentiment of text on social media, we propose a non-negative matrix tri-factorization (tri-NMF) based dual active supervision method to minimize human labeling efforts for the new type of data. Second, to make use of social media's real-time nature, we propose approaches to detect events from text streams on social media. Third, to address information overload for flexible information needs, we propose two summarization framework, dominating set based summarization framework and learning-to-rank based summarization framework. The dominating set based summarization framework can be applied for different types of summarization problems, while the learning-to-rank based summarization framework helps utilize the existing training data to guild the new summarization tasks. In addition, we integrate these techneques in an application study of event summarization for sports games as an example of how to better utilize social media data. ^

Text Analytics of Social Media: Sentiment Analysis, Event Detection and Summarization

In the last decade, large numbers of social media services have emerged and been widely used in people's daily life as important information sharing and acquisition tools. With a substantial amount of user-contributed text data on social media, it becomes a necessity to develop methods and tools for text analysis for this emerging data, in order to better utilize it to deliver meaningful information to users. Previous work on text analytics in last several decades is mainly focused on traditional types of text like emails, news and academic literatures, and several critical issues to text data on social media have not been well explored: 1) how to detect sentiment from text on social media; 2) how to make use of social media's real-time nature; 3) how to address information overload for flexible information needs. In this dissertation, we focus on these three problems. First, to detect sentiment of text on social media, we propose a non-negative matrix tri-factorization (tri-NMF) based dual active supervision method to minimize human labeling efforts for the new type of data. Second, to make use of social media's real-time nature, we propose approaches to detect events from text streams on social media. Third, to address information overload for flexible information needs, we propose two summarization framework, dominating set based summarization framework and learning-to-rank based summarization framework. The dominating set based summarization framework can be applied for different types of summarization problems, while the learning-to-rank based summarization framework helps utilize the existing training data to guild the new summarization tasks. In addition, we integrate these techneques in an application study of event summarization for sports games as an example of how to better utilize social media data.

Sentiment-Topic Modelling in Text Mining

Peer reviewed

Sentiment-Topic Modelling in Text Mining

Peer reviewed

A Curated Corpus for Sentiment-Topic Analysis

Postprint

Sentiment-Topic Modelling in Text Mining

Peer reviewed

Le sentiment d'appartenance à l'école : un regard conceptuel, psychométrique et théorique

Parce qu’il est notamment lié à des facteurs de réussite scolaire et d’adaptation sociale (Eccles & Roeser, 2009; Finn, 1989; Janosz, Georges, & Parent, 1998), le sentiment d’appartenance des élèves est considéré comme étant un élément de première instance qui doit d’être développé et maintenu par les professionnels de l’éducation (MELS, 2012). L'objectif général visait à approfondir notre compréhension du sentiment d’appartenance à l’école. Pour répondre à cet objectif général, trois articles de recherche distincts ont été élaborés. Le premier article présente une analyse conceptuelle visant à clarifier la compréhension du concept de sentiment d’appartenance à l’école. La méthode conceptuelle privilégiée dans cet article est celle de Walker et Avant (2011). La recension des écrits et les référents empiriques répertoriés indiquent que ce concept est de nature multidimensionnelle. L’analyse des données indique quatre attributs définitionnels. L’élève doit : (1) ressentir une émotion positive à l’égard du milieu scolaire; (2) entretenir des relations sociales de qualité avec les membres du milieu scolaire; (3) s’impliquer activement dans les activités de la classe ou celles de l’école; (4) percevoir une certaine synergie (harmonisation), voir même une similarité, avec les membres de son groupe. À la suite de cette étude permettant de mieux comprendre le sentiment d’appartenance à l’école, le deuxième article visait à examiner la structure factorielle et l'invariance de l’instrument de mesure du sentiment d’appartenance Psychological Sense of School Membership (PSSM) au regard du sexe des élèves. Cette étude a été menée chez un échantillon composé de 766 filles et de 391 garçons de troisième secondaire. Les analyses factorielles confirmatoires ont indiqué une structure à trois facteurs : (1) la qualité des relations entre les élèves; (2) la qualité des relations entre les élèves et l’enseignant; ainsi que (3) le sentiment d’acceptation par le milieu. Les analyses factorielles multigroupes ont indiqué pour leur part que le PSSM est un instrument invariant chez les filles et les garçons de troisième secondaire. Finalement, le troisième article a été mené chez un échantillon de 4166 élèves de niveau secondaire afin d’examiner les processus psychologiques complexes s’opérant entre le sentiment d’appartenance et le rendement scolaire (Anderman & Freeman, 2004; Connell & et al., 1994; Roeser et al., 1996). Afin d’examiner ces processus psychologiques, quatre hypothèses issues du modèle de Freeman-Anderman ont été validées par le biais d’analyses acheminatoires : H1 Les affects positifs médiatisent partiellement et positivement l’effet du sentiment d’appartenance sur l’engagement comportemental; H2 Les affects positifs médiatisent partiellement et positivement l’effet du sentiment d’appartenance sur l’engagement affectif; H3 Les affects positifs médiatisent partiellement et positivement l’effet du sentiment d’appartenance sur l’engagement cognitif; H4 Les engagements affectif, cognitif et comportemental médiatisent partiellement et positivement l’effet du sentiment d’appartenance sur le rendement scolaire. Nos résultats appuient partiellement la première hypothèse de recherche tout en soutenant les hypothèses deux, trois et quatre. Spécifiquement, la relation entre le sentiment d’appartenance et l’engagement émotionnel montre davantage un effet direct qu’un effet indirect (H2). L’étude a produit des résultats similaires pour l’engagement cognitif (H3). Finalement, la relation entre le sentiment d’appartenance et le rendement scolaire indique un effet indirect plus grand qu’un effet direct (H4). À la lumière de ces résultats, des recommandations à l’intention des professionnels de l’éducation sont offertes en guise de conclusion.

Le sentiment de compétence : modérateur du lien entre le QI et le rendement scolaire en mathématiques

La présente étude a pour but de vérifier si le QI et le sentiment de compétence interagissent lorsque l’élève doit performer à l’école et si, en l’occurrence, cette interaction est à son tour modérée par l’âge et le sexe des participants. Afin de vérifier ces hypothèses, les variables suivantes ont été étudiées chez 928 élèves de souche francocanadienne fréquentant des écoles montréalaises de niveau secondaire : la moyenne en mathématiques, le QI, le sentiment de compétence en mathématiques, l’âge, le sexe et le statut socioéconomique. Tel que prévu, le QI et le sentiment de compétence en mathématiques corrèlent de façon positive et significative avec la moyenne en mathématiques de l’élève. Les analyses montrent également une interaction significative entre le QI et le sentiment de compétence. Une fois décomposée, cette interaction indique que chez les élèves qui ont un sentiment de compétence élevé, la valeur prédictive du QI est plus élevée, alors que la relation entre le QI et la performance ne change pas de façon significative chez les élèves qui présentent un faible sentiment de compétence. Enfin, ni l’âge ni le sexe de l’élève n’influencent l’interaction entre le QI et le rendement scolaire, pas plus qu’ils ne sont corrélés avec le rendement scolaire. Les implications cliniques de cette recherche sont discutées.

Évaluation de l'efficacité de la pasteurisation à la vapeur pour le contrôle de la contamination microbiologique des carcasses bovines

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Efficacité des traitements physiothérapiques pour l'incontinence urinaire d'effort chez la femme en période postnatale

Thèse numérisée par la Direction des bibliothèques de l'Université de Montréal.