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.

Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN

Different types of sentences express sentiment in very different ways. Traditional sentence-level sentiment classification research focuses on one-technique-fits-all solution or only centers on one special type of sentences. In this paper, we propose a divide-and-conquer approach which first classifies sentences into different types, then performs sentiment analysis separately on sentences from each type. Specifically, we find that sentences tend to be more complex if they contain more sentiment targets. Thus, we propose to first apply a neural network based sequence model to classify opinionated sentences into three types according to the number of targets appeared in a sentence. Each group of sentences is then fed into a one-dimensional convolutional neural network separately for sentiment classification. Our approach has been evaluated on four sentiment classification datasets and compared with a wide range of baselines. Experimental results show that: (1) sentence type classification can improve the performance of sentence-level sentiment analysis; (2) the proposed approach achieves state-of-the-art results on several benchmarking datasets.

Sentiment analysis: la guerra russo-ucraina su twitter

Nel corso dell’elaborato verranno utilizzate tecniche e strumenti di analisi automatica di dati aventi carattere testuale. Lo scopo del lavoro di tesi consisterà nel condurre text mining e sentiment analysis su dei messaggi al fine di comprenderne il significato, con interesse particolare sulle emozioni ed i sentimenti in essi contenuti per riuscire ad estrapolare informazioni di interesse.

Concit-Corpus: Context Citation Analysis to learn Function, Polarity and Influence

Citation corpus composed by 85 articles taken randomly from ACL Anthology with a total of 2195 bibliography cites.

A Classification of Adjectives for Polarity Lexicons Enhancement

Subjective language detection is one of the most important challenges in Sentiment Analysis. Because of the weight and frequency in opinionated texts, adjectives are considered a key piece in the opinion extraction process. These subjective units are more and more frequently collected in polarity lexicons in which they appear annotated with their prior polarity. However, at the moment, any polarity lexicon takes into account prior polarity variations across domains. This paper proves that a majority of adjectives change their prior polarity value depending on the domain. We propose a distinction between domain dependent and romain independent adjectives. Moreover, our analysis led us to propose a further classification related to subjectivity degree: constant, mixed and highly subjective adjectives. Following this classification, polarity values will be a better support for Sentiment Analysis.

Automatic Extraction of Polar Adjectives for the Creation of Polarity Lexicons

Automatic creation of polarity lexicons is a crucial issue to be solved in order to reduce time andefforts in the first steps of Sentiment Analysis. In this paper we present a methodology based onlinguistic cues that allows us to automatically discover, extract and label subjective adjectivesthat should be collected in a domain-based polarity lexicon. For this purpose, we designed abootstrapping algorithm that, from a small set of seed polar adjectives, is capable to iterativelyidentify, extract and annotate positive and negative adjectives. Additionally, the methodautomatically creates lists of highly subjective elements that change their prior polarity evenwithin the same domain. The algorithm proposed reached a precision of 97.5% for positiveadjectives and 71.4% for negative ones in the semantic orientation identification task.

A linked data approach to sentiment and emotion analysis of twitter in the financial domain

Sentiment analysis has recently gained popularity in the financial domain thanks to its capability to predict the stock market based on the wisdom of the crowds. Nevertheless, current sentiment indicators are still silos that cannot be combined to get better insight about the mood of different communities. In this article we propose a Linked Data approach for modelling sentiment and emotions about financial entities. We aim at integrating sentiment information from different communities or providers, and complements existing initiatives such as FIBO. The ap- proach has been validated in the semantic annotation of tweets of several stocks in the Spanish stock market, including its sentiment information.

Summarizing threads in blogs using opinion polarity

The huge amount of data available on the Web needs to be organized in order to be accessible to users in real time. This paper presents a method for summarizing subjective texts based on the strength of the opinion expressed in them. We used a corpus of blog posts and their corresponding comments (blog threads) in English, structured around five topics and we divided them according to their polarity and subsequently summarized. Despite the difficulties of real Web data, the results obtained are encouraging; an average of 79% of the summaries is considered to be comprehensible. Our work allows the user to obtain a summary of the most relevant opinions contained in the blog. This allows them to save time and be able to look for information easily, allowing more effective searches on the Web.

Genome-wide analysis identifies a general requirement for polarity proteins in endocytic traffic

In a genome-wide RNA-mediated interference screen for genes required in membrane traffic - including endocytic uptake, recycling from endosomes to the plasma membrane, and secretion - we identified 168 candidate endocytosis regulators and 100 candidate secretion regulators. Many of these candidates are highly conserved among metazoans but have not been previously implicated in these processes. Among the positives from the screen, we identified PAR-3, PAR-6, PKC-3 and CDC-42, proteins that are well known for their importance in the generation of embryonic and epithelial-cell polarity. Further analysis showed that endocytic transport in Caenorhabditis elegans coelomocytes and human HeLa cells was also compromised after perturbation of CDC-42/Cdc42 or PAR-6/Par6 function, indicating a general requirement for these proteins in regulating endocytic traffic. Consistent with these results, we found that tagged CDC-42/Cdc42 is enriched on recycling endosomes in C. elegans and mammalian cells, suggesting a direct function in the regulation of transport.

A Curated Corpus for Sentiment-Topic Analysis

Postprint

Sentiment classification with case-base approach

L’augmentation de la croissance des réseaux, des blogs et des utilisateurs des sites d’examen sociaux font d’Internet une énorme source de données, en particulier sur la façon dont les gens pensent, sentent et agissent envers différentes questions. Ces jours-ci, les opinions des gens jouent un rôle important dans la politique, l’industrie, l’éducation, etc. Alors, les gouvernements, les grandes et petites industries, les instituts universitaires, les entreprises et les individus cherchent à étudier des techniques automatiques fin d’extraire les informations dont ils ont besoin dans les larges volumes de données. L’analyse des sentiments est une véritable réponse à ce besoin. Elle est une application de traitement du langage naturel et linguistique informatique qui se compose de techniques de pointe telles que l’apprentissage machine et les modèles de langue pour capturer les évaluations positives, négatives ou neutre, avec ou sans leur force, dans des texte brut. Dans ce mémoire, nous étudions une approche basée sur les cas pour l’analyse des sentiments au niveau des documents. Notre approche basée sur les cas génère un classificateur binaire qui utilise un ensemble de documents classifies, et cinq lexiques de sentiments différents pour extraire la polarité sur les scores correspondants aux commentaires. Puisque l’analyse des sentiments est en soi une tâche dépendante du domaine qui rend le travail difficile et coûteux, nous appliquons une approche «cross domain» en basant notre classificateur sur les six différents domaines au lieu de le limiter à un seul domaine. Pour améliorer la précision de la classification, nous ajoutons la détection de la négation comme une partie de notre algorithme. En outre, pour améliorer la performance de notre approche, quelques modifications innovantes sont appliquées. Il est intéressant de mentionner que notre approche ouvre la voie à nouveaux développements en ajoutant plus de lexiques de sentiment et ensembles de données à l’avenir.

Learning domain-specific sentiment lexicons with applications to recommender systems

Search is now going beyond looking for factual information, and people wish to search for the opinions of others to help them in their own decision-making. Sentiment expressions or opinion expressions are used by users to express their opinion and embody important pieces of information, particularly in online commerce. The main problem that the present dissertation addresses is how to model text to find meaningful words that express a sentiment. In this context, I investigate the viability of automatically generating a sentiment lexicon for opinion retrieval and sentiment classification applications. For this research objective we propose to capture sentiment words that are derived from online users’ reviews. In this approach, we tackle a major challenge in sentiment analysis which is the detection of words that express subjective preference and domain-specific sentiment words such as jargon. To this aim we present a fully generative method that automatically learns a domain-specific lexicon and is fully independent of external sources. Sentiment lexicons can be applied in a broad set of applications, however popular recommendation algorithms have somehow been disconnected from sentiment analysis. Therefore, we present a study that explores the viability of applying sentiment analysis techniques to infer ratings in a recommendation algorithm. Furthermore, entities’ reputation is intrinsically associated with sentiment words that have a positive or negative relation with those entities. Hence, is provided a study that observes the viability of using a domain-specific lexicon to compute entities reputation. Finally, a recommendation system algorithm is improved with the use of sentiment-based ratings and entities reputation.

Twitter data analysis for financial markets

Over the time, Twitter has become a fundamental source of information for news. As a one step forward, researchers have tried to analyse if the tweets contain predictive power. In the past, in financial field, a lot of research has been done to propose a function which takes as input all the tweets for a particular stock or index s, analyse them and predict the stock or index price of s. In this work, we take an alternative approach: using the stock price and tweet information, we investigate following questions. 1. Is there any relation between the amount of tweets being generated and the stocks being exchanged? 2. Is there any relation between the sentiment of the tweets and stock prices? 3. What is the structure of the graph that describes the relationships between users?

New markov chain based methods for single and cross-domain sentiment classification

Nowadays communication is switching from a centralized scenario, where communication media like newspapers, radio, TV programs produce information and people are just consumers, to a completely different decentralized scenario, where everyone is potentially an information producer through the use of social networks, blogs, forums that allow a real-time worldwide information exchange. These new instruments, as a result of their widespread diffusion, have started playing an important socio-economic role. They are the most used communication media and, as a consequence, they constitute the main source of information enterprises, political parties and other organizations can rely on. Analyzing data stored in servers all over the world is feasible by means of Text Mining techniques like Sentiment Analysis, which aims to extract opinions from huge amount of unstructured texts. This could lead to determine, for instance, the user satisfaction degree about products, services, politicians and so on. In this context, this dissertation presents new Document Sentiment Classification methods based on the mathematical theory of Markov Chains. All these approaches bank on a Markov Chain based model, which is language independent and whose killing features are simplicity and generality, which make it interesting with respect to previous sophisticated techniques. Every discussed technique has been tested in both Single-Domain and Cross-Domain Sentiment Classification areas, comparing performance with those of other two previous works. The performed analysis shows that some of the examined algorithms produce results comparable with the best methods in literature, with reference to both single-domain and cross-domain tasks, in $2$-classes (i.e. positive and negative) Document Sentiment Classification. However, there is still room for improvement, because this work also shows the way to walk in order to enhance performance, that is, a good novel feature selection process would be enough to outperform the state of the art. Furthermore, since some of the proposed approaches show promising results in $2$-classes Single-Domain Sentiment Classification, another future work will regard validating these results also in tasks with more than $2$ classes.

Expansión supervisada de léxicos polarizados adaptable al contexto

El análisis de opiniones es un área en la cual múltiples disciplinas han otorgado diferentes enfoques para elaborar modelos que sean capaces de extraer la polaridad de los textos analizados. En función del dominio o categoría del texto analizado, donde ejemplos de categorías son Deportes o Banca, estos modelos deben ser modificados para obtener un análisis de opinión de calidad. En esta tesis se presenta un modelo que pretende elaborar un análisis de opiniones independiente de la categoría a analizar y un extenso estado del arte sobre análisis de opiniones. Se propone un enfoque cuantitativo que haría uso de un léxico polarizado semilla como único recurso cualitativo del modelo. El enfoque propuesto hace uso de un corpus anotado de textos por polaridad y categoría y el léxico polarizado semilla para producir un modelo capaz de elaborar un análisis de opinión de calidad en las distintas categorías analizadas y expandir el léxico polarizado semilla con términos que se adecúan a las categorías procesadas.---ABSTRACT---Sentiment analysis is an area in which multiple disciplines have given diferent approaches to make models that are able to extract the polarity of the analyzed texts. Depending on the domain or category of the analyzed text, where examples of categories are Sports or Banking, these models should be modified to obtain a good opinion analysis. This thesis presents a model that aims to develop a category independent opinion analysis model and a extensive sentiment analysis state of the art. A quantitative approach is proposed that will use a polarized lexicon as the only qualitative resource. The proposed approach uses an annotated corpus by polarity and category and a polarized lexicon seed to produce a model able to develop a good opinion analysis in the various categories analyzed and to expand the polarized lexicon seed with terms that fit the processed categories.