Previous research has established that punctuation can be used to communicate nuances of meaning in online writing (McAndrew & De Jonge, 2011). Punctuation, considered a computer mediated communication (CMC) cue, expresses tone and emotion and disambiguates an author's intention (Vandergriff, 2013). Quotation marks as CMC cues can serve pragmatic functions and have been understudied. Some of these functions have been generally described (Predelli, 2003). However, no corpus study has specifically focused on the pragmatic uses of quotations in online text. Consumer reviews, a genre of online text, can directly impact business profits and influence customers' purchasing decisions (Floyd, Freling, Alhoqail, Cho & Freling, 2014). Businesses are investing in sentiment analysis to gauge their target market's opinions (Salehan & Kim, 2016). Sentiment analysis is the computerized appraisal of a text to determine whether its author is expressing a positive or negative opinion (Novak, Smailovic, Sluban & Mozetic, 2015). Sentiment analysis programs are still limited and could be improved in accuracy. Most programs rely on lexicons of words given a pre-determined polarity value (positive or negative) out of context (Novak et al., 2015). However, context is crucial to communication, and sentiment analysis programs could incorporate a better variety of contextual linguistic features to improve their accuracy. Quotations used for pragmatic communication is such a feature. This study discovered seven pragmatic quotation uses in a 2014 Yelp review corpus: Collective Knowledge, Non-standard, Grammatical, Non-literal, Narrative, Idiolect, and Emphasis. An ANOVA and Tukey HSD test were performed, and the results were significant. Pragmatic category accounted for 15% of the variance in review star rating. The Collective Knowledge category and the Narrative and Non-literal categories were significantly different from each other. The Collective Knowledge category showed a correlation with positive sentiment, while the Narrative and Non-literal categories displayed a correlation with negative sentiment. These three categories are likely present in several types of online text, making them valuable for further sentiment analysis research. If these pragmatic patterns could be detected automatically, they could be used in sentiment algorithms to give a more accurate picture of author opinion.

The field of authorship attribution seeks to characterize an author’s writing style well enough to determine whether he or she has written a text of interest. One subfield of authorship attribution, stylometry, seeks to find the necessary literary attributes to quantify an author’s writing style. The research presented here sought to determine the efficacy of sentiment analysis as a new stylometric feature, by comparing its performance in attributing authorship against the performance of traditional stylometric features. Experimentation, with a corpus of sci-fi texts, found sentiment analysis to have a much lower performance in assigning authorship than the traditional stylometric features.

Companies continually seek to improve their business model through feedback and customer satisfaction surveys. Social media provides additional opportunities for this advanced exploration into the mind of the customer. By extracting customer feedback from social media platforms, companies may increase the sample size of their feedback and remove bias often found in questionnaires, resulting in better informed decision making. However, simply using personnel to analyze the thousands of relative social media content is financially expensive and time consuming. Thus, our study aims to establish a method to extract business intelligence from social media content by structuralizing opinionated textual data using text mining and classifying these reviews by the degree of customer satisfaction. By quantifying textual reviews, companies may perform statistical analysis to extract insight from the data as well as effectively address concerns. Specifically, we analyzed a subset of 56,000 Yelp reviews on fast food restaurants and attempt to predict a quantitative value reflecting the overall opinion of each review. We compare the use of two different predictive modeling techniques, bagged Decision Trees and Random Forest Classifiers. In order to simplify the problem, we train our model to accurately classify strongly negative and strongly positive reviews (1 and 5 stars) reviews. In addition, we identify drivers behind strongly positive or negative reviews allowing businesses to understand their strengths and weaknesses. This method provides companies an efficient and cost-effective method to process and understand customer satisfaction as it is discussed on social media.

In the field of data mining, transfer learning is the method of transferring knowledge from one domain into another. Using reviews from prisjakt.se, a Swedish price comparison site, and hotels.com this work investigate how the similarities between domains affect the results of transfer learning when using recurrent neural networks. We test several different domains with different characteristics, e.g. size and lexical similarity. In this work only relatively similar domains were used, the same target function was sought and all reviews were in Swedish. Regardless, the results are conclusive; transfer learning is often beneficial, but is highly dependent on the features of the domains and how they compare with each other’s.

In a field as old as Classics, it difficult to find truly innovative approaches to literary works that have been studied for millennia, and it only becomes more difficult to find something new to explore in works as fundamental to the field as Marcus Tullius Cicero’s. However, in the burgeoning field of Digital Humanities, new avenues for textual exploration arise even among the over-picked rubble that is the Classical World. Through the use of computer software, we can search through and statistically analyze corpora of massive sizes. This project uses such techniques to perform a mesoanalysis of Cicero’s corpus. Through the use of R and Gephi, I will “read” Cicero’s works from a distance and see a much broader view of his character than I could through a traditional close reading of a few texts. This mesoanalysis includes a stylometric analysis of Cicero’s entire corpus, a sentiment analysis of his orations, and a network analysis of his letters. The sentiment analysis will explore Cicero as a literary figure. Through a hierarchical cluster analysis in R, I will assess not only how his style changes from genre to genre but within a genre (orations) as well. That analysis will close with an exploration of the lexical richness of his works, how it varies from genre to genre and over his lifetime. For the sentiment analysis, I built a lexicon based on Stoic theory, primarily as it is explained in the Tusculunae Disputationes, and Robert Kaster’s work with emotional scripts. After the lexicon was built, I applied it to Cicero’s orations in a method similar to Matthew Jockers’ syuzhet package for R, and I traced his use of sentiment across the speech. I then compared those trajectories to Latin rhetorical theory, especially the theories included in Cicero’s own treatises, in order to see if Cicero had put into effect his own advice or if he had a few techniques that he kept hidden. The mesoanalysis closes with a network analysis of the Epistulae ad Familiares. I merged Cicero’s social network with a sentiment analysis in order to assess how Cicero felt about and interacted with his peers. From this analysis, one could gather an idea of Cicero as a person. At the end of the mesoanalysis, we can attain a much broader sense of Cicero’s character. This project also has a second aim, and that is to explain how these techniques could be applied to other literary corpora, outside of Cicero’s and Latin. I have carefully detailed my process and provide more instruction in my appendices so that readers could attempt these analyses and be successful in them.

Deep Learning models rely on a huge amount of labeled data to be created. However, there are a number of areas where labeling data is a costly process, making Deep Learning approaches unfeasible. One way to handle that situation is by using the Active Learning technique. Initially, it creates a model with the available labeled data. After that, it incrementally chooses new unlabeled data that will potentially increase the model accuracy, if added to the training data. To select which data will be labeled next, this technique requires a measurement of uncertainty from the model prediction, which is usually not computed for Deep Learning methods. A new approach has been proposed to measure uncertainty in those models, called Monte Carlo Dropout . This technique allowed Active Learning to be used together with Deep Learning for image classification. This research will evaluate if modeling uncertainty on Deep Learning models with Monte Carlo Dropout will make the use of Active Learning feasible for the task of sentiment analysis, an area with huge amount of data, but few of them labeled. / Modelos de Aprendizado Profundo necessitam de uma vasta quantidade de dados anotados para serem criados. Entretanto, existem muitas áreas onde obter dados anotados é uma tarefa custosa. Neste cenário, o uso de Aprendizado Profundo se torna bastante difícil. Uma maneira de lidar com essa situação é usando a técnica de Aprendizado Ativo. Inicialmente, essa técnica cria um modelo com os dados anotados disponíveis. Depois disso, ela incrementalmente escolhe dados não anotados que irão, potencialmente, melhorar à acurácia do modelo, se adicionados aos dados de treinamento. Para selecionar quais dados serão anotados, essa técnica necessita de uma medida de incerteza sobre as predições geradas pelo modelo. Entretanto, tal medida não é usualmente realizada em modelos de Aprendizado Profundo. Uma nova técnica foi proposta para lidar com a problemática de medir a incerteza desses modelos, chamada de Monte Carlo Dropout . Essa técnica permitiu o uso de Aprendizado Ativo junto com Aprendizado Profundo para tarefa de classificação de imagens. Essa pesquisa visa averiguar se ao modelarmos a incerteza em modelos de Aprendizado Profundo com a técnica de Monte Carlo Dropout , será possível usar a técnica de Aprendizado Ativo para tarefa de análise de sentimento, uma área com uma vasta quantidade de dados, mas poucos deles anotados.

The world in which we live has changed rapidly over the last few decades. Threats of bioterrorism, influenza pandemics, and emerging infectious diseases coupled with unprecedented population mobility led to the development of public health surveillance systems. These systems are useful in detecting and responding to infectious disease outbreaks but often operate with a considerable delay and fail to provide the necessary lead time for optimal public health response. In contrast, syndromic surveillance systems rely on clinical features (e.g., activities prompted by the onset of symptoms) that are discernible prior to diagnosis to warn of changes in disease activity. Although less precise, these systems can offer considerable lead time. Patient information may be acquired from multiple existing sources established for other purposes, including, for example, emergency department primary complaints, ambulance dispatch data, and over-the-counter medication sales. Unfortunately, these data are often expensive, sometimes difficult to obtain and almost always hard to integrate. Fortunately, the proliferation of online social networks makes much more information about our daily habits and lifestyles freely available and easily accessible on the web. Twitter, Facebook and FourSquare are only a few examples of the many websites where people voluntarily post updates on their daily behaviors, health status, and physical location. In this thesis we develop and apply methods to collect, filter and analyze the content of social media postings in order to make predictions. As a proof of concept we used Twitter data to predict public opinion in the form of the outcome of a popular television show. We then used the same methods to monitor and track public perception of influenza during the H1N1 epidemic, and even to predict disease burden in real time, which is a measurable advance over current public health practice. Finally, we used location specific social media data to model human travels and show how this data can improve our prediction of disease burden.

Esta Tese tem como objetivo geral inserir a Análise de Sentimentos na gestão das Cidades Inteligentes, possibilitando a implementação de uma ferramenta que disponibilize informações que auxiliem na supervisão e gestão dessas cidades. Dentre os possíveis auxílios que podem ser prestados está a identificação de ações, meios de prevenção e predição de possíveis adversidades nos diversos Domínios de Interesse, além da busca por melhorias na qualidade vida da população, que pode ser feita por meio dessa análise, permitindo que os gestores dessas cidades possam tomar as melhores decisões de acordo com cada cenário. Este trabalho contribui com um novo método cujo o objetivo é o desenvolvimento de um Sistema de Análise de Sentimentos para Auxílio na Gestão das Cidades Inteligentes (ASCI). Esse Sistema é capaz de captar, tratar, processar, filtrar por Domínio de Interesse e avaliar os sentimentos contidos nas informações provenientes dos cidadãos de uma Cidade Inteligente. O método utiliza duas Fases de Mineração de Dados, uma para a classificação dos Domínios de Interesse e outra para a Análise de Sentimentos. Para o estudo de caso foi implementado o método ASCI por meio do qual são captadas informações provenientes da população de uma determinada região da cidade de São Paulo, por meio da Rede Social Twitter. Também foi realizado um estudo de classificação de sentimentos no Domínio específico do Transporte, no qual também foram utilizados, e tiveram seu desempenho avaliado, os classificadores do tipo Linear SVC, Logistic Regression, Multinomial Naive Bayes e Random Forest Classifier para identificar os sentimentos positivos, neutros e negativos dos tweets captados. Os dados foram avaliados usando duas técnicas de extração de características de texto: Bag of Words e TF-IDF. O método ASCI desenvolvido nesta Tese contribui de maneira relevante para a área de Análise de Sentimentos, uma vez que os resultados obtidos foram satisfatórios quando aplicado em cenários de Domínios de Interesse das Cidades Inteligentes. / The main objective of this work is to insert the Sentiment Analysis in the management of Smart Cities, enabling the implementation of a supervision and management tool in these cities. Among the possible aid services that can be applied, there is the identification of actions, ways of prevention and prediction of possible adversities in the various Domains of Interest, and also the search for improvements in the quality of life of the population. This can be done through this analysis, allowing the best decisions according to each scenario by the city managers. This work contributes to a new method whose objective is the development of a Sentiment Analysis System to Assist in the Management of Smart Cities (ASCI). This System is capable of capturing, classifying, processing, filtering by Domain of Interest and evaluating the sentiments of Smart City citizens. The method uses two Data Mining phases, one for the classification of Domains of Interest and the other for Sentiment Analysis. For the case study, the ASCI method was implemented, through which information was collected from a regional population in São Paulo city through Twitter Social Network data. A study of Sentiment Analysis in specific Domain of Interest Transport was also carried out, in which Linear SVC, Logistic Regression, Multinomial Naive Bayes and Random Forest classifiers were used to identify the positive, neutral and negative sentiments of collected tweets. The data were evaluated using two techniques of extraction of text characteristics: Bag of Words and TF-IDF. The ASCI method developed in this Thesis contributes significantly to the area of Sentiment Analysis and the results obtained were satisfactory when applied in Smart City Domain of Interest scenarios.

Social media offers a powerful outlet for people's thoughts and feelings -- it is an enormous ever-growing source of texts ranging from everyday observations to involved discussions. This thesis contributes to the field of sentiment analysis, which aims to extract emotions and opinions from text. A basic goal is to classify text as expressing either positive or negative emotion. Sentiment classifiers have been built for social media text such as product reviews, blog posts, and even Twitter messages. With increasing complexity of text sources and topics, it is time to re-examine the standard sentiment extraction approaches, and possibly to re-define and enrich sentiment definition. Thus, this thesis begins by introducing a rich multi-dimensional model based on Affect Control Theory and showing its usefulness in sentiment classification. Next, unlike sentiment analysis research to date, we examine sentiment expression and polarity classification within and across various social media streams by building topical datasets. When comparing Twitter, reviews, and blogs on consumer product topics, we show that it is possible, and sometimes even beneficial, to train sentiment classifiers on text sources which are different from the target text. This is not the case, however, when we compare political discussion in YouTube comments to Twitter posts, demonstrating the difficulty of political sentiment classification. We further show that neither discussion volume or sentiment expressed in these streams correspond well to national polls, putting in question recent research linking the two. The complexity of political discussion also calls for a more specific re-definition of "sentiment" as agreement with the author's political stance. We conclude that sentiment must be defined, and tools for its analysis designed, within a larger framework of human interaction.

With a growing amount of subjective content distributed across the Web, there is a need for a domain-independent information retrieval system that would support ad hoc retrieval of documents expressing opinions on a specific topic of the user’s query. While the research area of opinion detection and sentiment analysis has received much attention in the recent years, little research has been done on identifying subjective content targeted at a specific topic, i.e. expressing topical opinion. This thesis presents a novel method for ad hoc retrieval of documents which contain subjective content on the topic of the query. Documents are ranked by the likelihood each document expresses an opinion on a query term, approximated as the likelihood any occurrence of the query term is modified by a subjective adjective. Domain-independent user-based evaluation of the proposed methods was conducted, and shows statistically significant gains over Google ranking as the baseline.