This work is concerned with the automatic understanding of evaluative text. We investigate sentence level opinion polarity prediction by assigning lexical polarities and deriving sentence polarity from these with the use of contextual valence shifters. A methodology for iterative failure analysis is developed and used to refine our lexicon and identify new contextual shifters. Algorithms are presented that employ these new shifters to improve sentence polarity prediction accuracy beyond that of a state-of-the-art existing algorithm in the domain of consumer product reviews. We then apply the best configuration of our algorithm to the domain of movie reviews.

This work is concerned with the automatic understanding of evaluative text. We investigate sentence level opinion polarity prediction by assigning lexical polarities and deriving sentence polarity from these with the use of contextual valence shifters. A methodology for iterative failure analysis is developed and used to refine our lexicon and identify new contextual shifters. Algorithms are presented that employ these new shifters to improve sentence polarity prediction accuracy beyond that of a state-of-the-art existing algorithm in the domain of consumer product reviews. We then apply the best configuration of our algorithm to the domain of movie reviews.

This work is concerned with the automatic understanding of evaluative text. We investigate sentence level opinion polarity prediction by assigning lexical polarities and deriving sentence polarity from these with the use of contextual valence shifters. A methodology for iterative failure analysis is developed and used to refine our lexicon and identify new contextual shifters. Algorithms are presented that employ these new shifters to improve sentence polarity prediction accuracy beyond that of a state-of-the-art existing algorithm in the domain of consumer product reviews. We then apply the best configuration of our algorithm to the domain of movie reviews. / Science, Faculty of / Computer Science, Department of / Graduate

With the upsurge of Web 2.0, customers are able to share their opinions and feelings about products and services, politics, economic shifts, current events and any number of other topics on the Web. This information, if leveraged effectively, can provide rich and valuable insights, such as: input for vendors to create successful marketing strategies, understanding of areas of improvement in products and services and tracking political opinion. The problem with this information is that it is unorganised and unstructured, therefore, it is difficult to assess automatically and in bulk. Studies in the field of sentiment analysis aim to provide a solution to determining the polarities of, and gain an overview of, the wider public opinion behind certain topics in a large volume of textual data. This research provides a novel framework and a solid, practical implementation of the proposed framework for fine-grained sentiment analysis. The framework supports mixed-opinion text and multiword expressions when analysing the sentiments expressed and the aspects that those sentiments relate to. This research uses datasets across two domains in the customer reviews area (phone products and hotel services) to evaluate the proposed framework for its reliability and validity. A sizeable performance improvement was noted whereby the proposed methodology yielded a result of 91.3% accuracy in sentiment classification, as compared to the baseline (SentiWordNet), which had a result of 71.0%. In addition, an accuracy of 92.5% was observed for the aspect analysis automatically generated across the two domains tested.

Recommender systems (RSs) provide personalised suggestions of information or products relevant to user's needs. RSs are considered as powerful tools that help users to find interesting items matching their own taste. Although RSs have made substantial progress in theory and algorithm development and have achieved many commercial successes, how to utilise the widely available information on Online Social Networks (OSNs) has largely been overlooked. Noticing this gap in existing research on RSs and taking into account a user's selection being greatly influenced by his/her trusted friends and their opinions, this thesis proposes a novel personalised Recommender System framework, so-called Implicit Social Trust and Sentiment (ISTS) based RSs. The main motivation was to overcome the overlooked use of OSNs in Recommender Systems and to utilise the widely available information from such networks. This work also designs solutions to a number of challenges inherent to the RSs domain, such as accuracy, cold-start, diversity and coverage. ISTS improves the existing recommendation approaches by exploring a new source of data from friends' short posts in microbloggings. In the case of new users who have no previous preferences, ISTS maps the suggested recommendations into numerical rating scales by applying the three main components. The first component is measuring the implicit trust between friends based on their intercommunication activities and behaviour. Owing to the need to adapt friends' opinions, the implicit social trust model is designed to include the trusted friends and give them the highest weight of contribution in recommendation encounter. The second component is inferring the sentiment rating to reflect the knowledge behind friends' short posts, so-called micro-reviews. The sentiment behind micro-reviews is extracted using Sentiment Analysis (SA) techniques. To achieve the best sentiment representation, our approach considers the special natural environment in OSNs brief posts. Two Sentiment Analysis methodologies are used: a bag of words method and a probabilistic method. The third ISTS component is identifying the impact degree of friends' sentiments and their level of trust by using machine learning algorithms. Two types of machine learning algorithms are used: classification models and regressions models. The classification models include Naive Bayes, Logistic Regression and Decision Trees. Among the three classification models, Decision Trees show the best Mean absolute error (MAE) at 0.836. Support Vector Regression performed the best among all models at 0.45 of MAE. This thesis also proposes an approach with further improvement over ISTS, namely Hybrid Implicit Social Trust and Sentiment (H-ISTS). The enhanced approach applies improvements by optimising trust parameters to identify the impact of the features (re-tweets and followings/followers list) on recommendation results. Unlike the ISTS which allocates equal weight to trust features, H-ISTS provides different weights to determine the different effects of the two trust features. As a result, we found that H-ISTS improved the MAE to be 0.42 which is based on Support Vector Regression. Further, it increases the number of trust features from two to five features in order to include the influence of these features in rating predictions. The integration of the new approach H-ISTS with a Collaborative Filtering recommender system, in particular memory-based, is investigated next. Therefore, existing users with a history of ratings can receive recommendations by fusing their own tastes and their friends' preferences using the two type of memory-based methods: user-based and item-based. H-ISTSitem is the integration of H-ISTS and item-based which provides the lowest error at 0.7091. The experiments show that diversity is better achieved using the H-ISTSuser which is the integration of H-ISTS and user-based technique. To evaluate the performance of these approaches, two real social datasets are collected from Twitter. To verify the proposed framework, the experiments are conducted and the results are compared against the most relevant baselines which confirmed that RSs have been successfully improved using OSNs. These enhancements demonstrate the effectiveness and promises of the proposed approach in RSs.

The success of on-line review websites has led to an overwhelming number of on-line consumer reviews. These reviews have become an important tool for consumers when making a decision to purchase a product. This growth has led to the need for applications that enable this information to be presented in a way that is meaningful. These applications often rely on domain specific semantic lexicons which are both expensive and time consuming to make. The following thesis proposes an unsupervised approach for product aspect discovery in on-line consumer reviews. We apply a two step hierarchical clustering process in which we first cluster based on the semantic similarity of the contexts of terms and then on the similarity of the hypernyms of the cluster members. The method also includes a process for assigning class labels to each of the clusters. Finally an experiment showing how the proposed methods can be used to measure aspect based sentiment is performed. The methods proposed in this thesis are evaluated on a set of 157,865 reviews from a major commercial website and found that the two-step clustering process increases cluster F-scores over a single round of clustering. Finally, the proposed methods are compared to a state of the art topic modelling approach by Titov and McDonald (2008).

abstract: In this thesis multiple approaches are explored to enhance sentiment analysis of tweets. A standard sentiment analysis model with customized features is first trained and tested to establish a baseline. This is compared to an existing topic based mixture model and a new proposed topic based vector model both of which use Latent Dirichlet Allocation (LDA) for topic modeling. The proposed topic based vector model has higher accuracies in terms of averaged F scores than the other two models. / Dissertation/Thesis / Masters Thesis Computer Science 2016

abstract: Social media refers computer-based technology that allows the sharing of information and building the virtual networks and communities. With the development of internet based services and applications, user can engage with social media via computer and smart mobile devices. In recent years, social media has taken the form of different activities such as social network, business network, text sharing, photo sharing, blogging, etc. With the increasing popularity of social media, it has accumulated a large amount of data which enables understanding the human behavior possible. Compared with traditional survey based methods, the analysis of social media provides us a golden opportunity to understand individuals at scale and in turn allows us to design better services that can tailor to individuals’ needs. From this perspective, we can view social media as sensors, which provides online signals from a virtual world that has no geographical boundaries for the real world individual's activity. One of the key features for social media is social, where social media users actively interact to each via generating content and expressing the opinions, such as post and comment in Facebook. As a result, sentiment analysis, which refers a computational model to identify, extract or characterize subjective information expressed in a given piece of text, has successfully employs user signals and brings many real world applications in different domains such as e-commerce, politics, marketing, etc. The goal of sentiment analysis is to classify a user’s attitude towards various topics into positive, negative or neutral categories based on textual data in social media. However, recently, there is an increasing number of people start to use photos to express their daily life on social media platforms like Flickr and Instagram. Therefore, analyzing the sentiment from visual data is poise to have great improvement for user understanding. In this dissertation, I study the problem of understanding human sentiments from large scale collection of social images based on both image features and contextual social network features. We show that neither visual features nor the textual features are by themselves sufficient for accurate sentiment prediction. Therefore, we provide a way of using both of them, and formulate sentiment prediction problem in two scenarios: supervised and unsupervised. We first show that the proposed framework has flexibility to incorporate multiple modalities of information and has the capability to learn from heterogeneous features jointly with sufficient training data. Secondly, we observe that negative sentiment may related to human mental health issues. Based on this observation, we aim to understand the negative social media posts, especially the post related to depression e.g., self-harm content. Our analysis, the first of its kind, reveals a number of important findings. Thirdly, we extend the proposed sentiment prediction task to a general multi-label visual recognition task to demonstrate the methodology flexibility behind our sentiment analysis model. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2018

Consumer's opinions and sentiments on products can reflect the performance of products in general or in various aspects. Analyzing these data is becoming feasible, considering the availability of immense data and the power of natural language processing. However, retailers have not taken full advantage of online comments. This work is dedicated to a solution for automatically analyzing and summarizing these valuable data at both product and category levels. In this research, a system was developed to retrieve and analyze extensive data from public online resources. A parallel framework was created to make this system extensible and efficient. In this framework, a star topological network was adopted in which each computing unit was assigned to retrieve a fraction of data and to assess sentiment. Finally, the preprocessed data were collected and summarized by the central machine which generates the final result that can be rendered through a web interface. The system was designed to have sound performance, robustness, manageability, extensibility, and accuracy.

El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado. / In recent years, the increased use of digital tools within the Peruvian tourism industry has created a corresponding increase in revenues. However, both factors have caused increased competition in the sector that in turn puts pressure on small and medium enterprises’ (SME) revenues and profitability. This study aims to apply neural network based sentiment analysis on social networks to generate a new information search channel that provides a global understanding of user trends and preferences in the tourism sector. A working data-analysis framework will be developed and integrated with tools from the cloud to allow a visual assessment of high probability outcomes based on historical data, to help SMEs estimate the number of tourists arriving and places they want to visit, so that they can generate desirable travel packages in advance, reduce logistics costs, increase sales, and ultimately improve both quality and precision of customer service.