O sucesso da mineração de opiniões para processar automaticamente grandes quantidades de conteúdo opinativo disponíveis na Internet tem sido demonstrado como uma solução de baixa latência e mais barata para a análise de opinião pública. No presente trabalho foi investigado se é possível prever variações de intenção de voto com base em séries temporais de sentimento extraídas de comentários de notícias, utilizando três eleições brasileiras como estudo de caso. As contribuições deste estudo de caso são: a) a comparação de duas abordagens para a mineração de opiniões em conteúdo gerado por usuários em português do Brasil; b) a proposta de dois tipos de atributos discriminantes para representar o sentimento em relação a candidatos políticos a serem usados para a previsão, c) uma abordagem para prever variações de intenção de voto que é adequada para cenários de dados esparsos. Foram desenvolvidos experimentos para avaliar a influência dos atributos discriminantes propostos em relação a acurácia da previsão, e suas respectivas preparações. Os resultados mostraram uma acurácia de 70% na previsão de variações de intenção de voto positivas e negativas. Estas contribuições são importantes passos em direção a um framework que é capaz de combinar opiniões de diversas fontes para encontrar a representatividade de uma população alvo, de modo que se possa obter previsões mais confiáveis. / The success of opinion mining for automatically processing vast amounts of opinionated content available on the Internet has been demonstrated as a less expensive and lower latency solution for gathering public opinion. In this work, we investigate whether it is possible to predict variations in vote intention based on sentiment time series extracted from news comments, using three Brazilian elections as case study. The contributions of this case study are: a) the comparison of two approaches for opinion mining in user-generated content in Brazilian Portuguese; b) the proposition of two types of features to represent sentiment behavior towards political candidates that can be used for prediction, c) an approach to predict polls vote intention variations that is adequate for scenarios of sparse data. We developed experiments to assess the influence on the forecasting accuracy of the proposed features, and their respective preparation. Our results display an accuracy of 70% in predicting positive and negative variations. These are important contributions towards a more general framework that is able to blend opinions from several different sources to find representativeness of the target population, and make more reliable predictions.

abstract: Using integrated threat theory as the theoretical framework, this study examines the impact of perceived realistic threats (threats to welfare) and symbolic threats (threats to worldview) on anti-immigrant sentiment among a nationally representative sample in the U.S. Analysis of the antecedents of prejudice is particularly relevant today as anti-immigrant sentiment and hostile policies toward the population have risen in the past two decades. Perceived discrimination has also become salient within immigrant communities, negatively impacting both mental and physical health. Using logistic ordinal regressions with realistic threat, symbolic threat, and immigrant sentiment scales, this study found that both realistic and symbolic threats increased participants' likelihood of selecting a higher level of anti-immigrant sentiment, suggesting both are predictive of prejudice. However, symbolic threats emerged as a greater predictor of anti-immigrant sentiment, with an effect size over twice that of realistic threats. Implications for social work policy, practice, and future research are made. / Dissertation/Thesis / M.S.W. Social Work 2014

Sentiment analysis concerns the computational study of opinions expressed in text. Social media domains provide a wealth of opinionated data, thus, creating a greater need for sentiment analysis. Typically, sentiment lexicons that capture term-sentiment association knowledge are commonly used to develop sentiment analysis systems. However, the nature of social media content calls for analysis methods and knowledge sources that are better able to adapt to changing vocabulary. Invariably existing sentiment lexicon knowledge cannot usefully handle social media vocabulary which is typically informal and changeable yet rich in sentiment. This, in turn, has implications on the analyser's ability to effectively capture the context therein and to interpret the sentiment polarity from the lexicons. In this thesis we use SentiWordNet, a popular sentiment-rich lexicon with a substantial vocabulary coverage and explore how to adapt it for social media sentiment analysis. Firstly, the thesis identifies a set of strategies to incorporate the effect of modifiers on sentiment-bearing terms (local context). These modifiers include: contextual valence shifters, non-lexical sentiment modifiers typical in social media and discourse structures. Secondly, the thesis introduces an approach in which a domain-specific lexicon is generated using a distant supervision method and integrated with a general-purpose lexicon, using a weighted strategy, to form a hybrid (domain-adapted) lexicon. This has the dual purpose of enriching term coverage of the general purpose lexicon with non-standard but sentiment-rich terms as well as adjusting sentiment semantics of terms. Here, we identified two term-sentiment association metrics based on Term Frequency and Inverse Document Frequency that are able to outperform the state-of-the-art Point-wise Mutual Information on social media data. As distant supervision may not be readily applicable on some social media domains, we explore the cross-domain transferability of a hybrid lexicon. Thirdly, we introduce an approach for improving distant-supervised sentiment classification with knowledge from local context analysis, domain-adapted (hybrid) and emotion lexicons. Finally, we conduct a comprehensive evaluation of all identified approaches using six sentiment-rich social media datasets.

En prenant pour toile de fond l’analyse de la métaphysique du dualisme cartésien de substances, la présente thèse a pour objectif de discuter la question de savoir quel serait le sujet des prédicats qui dénotent des sentiments dans les textes de Descartes. L’hypothèse proposée est que seules substances peuvent être considérées comme des « sujets ultimes d’inhérence » de ces prédicats. Pourtant, il sera argumenté que les hommes et les animaux, qui ne sont pas des substances, peuvent être considérés comme les « sujets d’attribution » de ces prédicats, puisqu’ils possèdent un type spécial d’unité, à savoir, une « unité de composition », qui assure une telle attribution. Ainsi, la thèse sera développée selon trois axes principaux. En partant d’un examen de la théorie cartésienne de la substance et de ses définitions, nous analyserons le concept de substance étendue, en prenant compte du débat entre les interprétations moniste et pluraliste de ce concept. Dans ce contexte, nous examinerons la spécificité du corps humain par rapport aux autres corps de la nature, en considérant certains aspects de la théorie cartésienne des animaux-machines. Ensuite, nous discuterons la question de l’unité de l’homme, ainsi que d’autres types d’unité reconnus par Descartes. Finalement, nous analyserons la théorie cartésienne de la causalité dans le but de déterminer quelles théories parmi celles de la causalité, interactionniste ou occasionaliste, pourraient servir, dans la vision de Descartes, de modèles explicatifs des sentiments humains et des sentiments animaux. L’hypothèse défendue dans cette thèse est en consonance avec la vision selon laquelle la théorie cartésienne des trois notions primitives particulières, à savoir, pensée, étendue et union, est totalement compatible avec le dualisme métaphysique de substances que Descartes propose et, par conséquent, n’implique pas un affaiblissement de ce dernier. / The goal of this thesis is to address the question of what would be the subject of the predicates that denote sentiments in Descartes’ writings. The proposed hypothesis is that substances can only be regarded as « the ultimate subjects of inherence » of these predicates. Nevertheless, it will be argued that men and animals, although they are not substances, may be considered the « subjects of attribution » of such predicates, since they have a specific unit, namely, a « unity of composition », which ensures that attribution. Therefore, the thesis will be developed in three main axes. From an examination of the Cartesian theory of substance and its definitions, we analyze the concept of extended substance, taking into account the existing debate between monistic and pluralistic interpretations of this concept. In this context, we examine the specificity of the human body in relation to other bodies of nature, considering certain aspects of the Cartesian theory of animal machines. Then we address the question of the unity of man, as well as other types of unity recognized by Descartes. Finally, we examine the Cartesian theory of causality in order to determine which theories of causality, interactionism, or occasionalism, in Descartes view, could serve as explanatory models for sentiments in humans and animals. The hypothesis to be defended in this thesis is consistent with the view that the Cartesian theory of three particular primitive notions, namely, thought, extension, and union, is fully compatible with the metaphysical dualism of substances that Descartes proposed, and therefore does not imply a weakening of the latter.

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.

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.

A major security risk with the use of a Java logging library called Log4j was discovered in November 2021. The vulnerability meant that all Java applications using Log4j could be exploited by hackers through remote code execution. The Log4j vulnerability came to the general public's knowledge and became a hot topic on various social media platforms the 9th of December 2021. This is what will be referred to as the Log4j incident in this paper. The aim of the study is to investigate what attitudes users on Twitter have towards Log4j and how these attitudes have evolved over time in relation to the incident in question. Twitter data regarding Log4j was collected using Twitter API and sentiment analysis was performed on the data set using VADER. The gathered tweets were classified as either positive, negative or neutral. The data was collected, sorted and analyzed based on the CRISP-DM methodology. Tweets from two different time periods were studied. The two periods were 1) five months prior to the incident and 2) five months after the incident. The results showed that tweets posted before the incident were mostly positive, while tweets posted after the incident were mostly negative. An interesting discovery was found when comparing the sentiments exhibited within the five-month period directly following the incident. During the first month the results exhibited a predominance of negative sentiment regarding Log4j, while April 2022 on the contrary, was predominantly positive. In conclusion this study has presented the results of the attitudes a large group of Twitter users have expressed towards Log4j and how these attitudes have evolved over time. A gap in related research of how the discussions on social media circulate when a security threat with great impact appears has been identified and this study aims to provide new insights within this area.

With the rise of social media and publicly available data, opinion mining is more accessible than ever. It is valuable for content creators, companies and advertisers to gain insights into what users think and feel. This work examines comments on YouTube videos, and builds a deep learning classifier to automatically determine their sentiment. Four Long Short-Term Memory-based models are trained and evaluated. Experiments are performed to determine which deep learning model performs with the best accuracy, recall, precision, F1 score and ROC curve on a labelled YouTube Comment dataset. The results indicate that a BiLSTM-based model has the overall best performance, with the accuracy of 89%. Furthermore, the four LSTM-based models are evaluated on an IMDB movie review dataset, achieving an average accuracy of 87%, showing that the models can predict the sentiment of different textual data. Finally, a statistical analysis is performed on the YouTube videos, revealing that videos with positive sentiment have a statistically higher number of upvotes and views. However, the number of downvotes is not significantly higher in videos with negative sentiment.

<p>When people write a review about a business, they write and rate it based on their personal experience of the business. Sentiment analysis is a natural language processing technique that determines the sentiment of text, including reviews. However, unlike computers, the personal experience of humans emphasizes their preferences and observations that they deem important while ignoring other components that may not be as important to them personally. Traditional sentiment analysis does not consider such preferences. To utilize these human preferences in sentiment analysis, this paper explores various methods of weighting aspects in an attempt to improve sentiment analysis accuracy. Two types of methods are considered. The first method applies human preference by assigning weights to aspects in calculating overall sentiment analysis. The second method uses the results of the first method to improve the accuracy of traditional supervised sentiment analysis. The results show that the methods have high accuracy when people have strong opinions, but the weights of the aspects do not significantly improve the accuracy.</p>

No description available.