Opinion Mining

In this thesis we study the field of opinion mining by giving a comprehensive review of the available research that has been done in this topic. Also using this available knowledge we present a case study of a multilevel opinion mining system for a student organization's sales management system. We describe the field of opinion mining by discussing its historical roots, its motivations and applications as well as the different scientific approaches that have been used to solve this challenging problem of mining opinions. To deal with this huge subfield of natural language processing, we first give an abstraction of the problem of opinion mining and describe the theoretical frameworks that are available for dealing with appraisal language. Then we discuss the relation between opinion mining and computational linguistics which is a crucial pre-processing step for the accuracy of the subsequent steps of opinion mining. The second part of our thesis deals with the semantics of opinions where we describe the different ways used to collect lists of opinion words as well as the methods and techniques available for extracting knowledge from opinions present in unstructured textual data. In the part about collecting lists of opinion words we describe manual, semi manual and automatic ways to do so and give a review of the available lists that are used as gold standards in opinion mining research. For the methods and techniques of opinion mining we divide the task into three levels that are the document, sentence and feature level. The techniques that are presented in the document and sentence level are divided into supervised and unsupervised approaches that are used to determine the subjectivity and polarity of texts and sentences at these levels of analysis. At the feature level we give a description of the techniques available for finding the opinion targets, the polarity of the opinions about these opinion targets and the opinion holders. Also at the feature level we discuss the various ways to summarize and visualize the results of this level of analysis. In the third part of our thesis we present a case study of a sales management system that uses free form text and that can benefit from an opinion mining system. Using the knowledge gathered in the review of this field we provide a theoretical multi level opinion mining system (MLOM) that can perform most of the tasks needed from an opinion mining system. Based on the previous research we give some hints that many of the laborious market research tasks that are done by the sales force, which uses this sales management system, can improve their insight about their partners and by that increase the quality of their sales services and their overall results.

Slutrapport. Projektet ”Svensk politik i Finland – beteende, opinion, framtid” 2007-2010

Slutrapport

Political ideologies and attitudes towards income inequality in the US: a critical discourse analysis of CNN and Fox News opinion articles

The topic of the thesis is media discourse about current state if income inequality in the US, and political ideologies as influences behind the discourse. The data consists of four opinion articles, two from CNN and two from Fox News. The purpose of the study was to examine how media represents income inequality as an issue, and if the attitudes conveyed are concerned or indifferent. Previous studies have indicated that the level of income is often seen as a personal responsibility, and such perspective can be linked with Republican ideology. In contrast, the Democrats typically express more concern about the consequences of inequality. CNN has been previously considered to have a Democratic bias, and Fox News has been considered to have Republican bias, which is one reason why these two news channels were chosen as the sources of the data. The study is a critical discourse analysis, and the methods applied were sociocognitive approach, which analyzes the social and cognitive factors affecting the discourse, and appraisal framework, which was applied to scrutinize the expressed attitudes more closely by identifyind specific linguistic features. The appraisal framework includes studying such features as affect, judgment and appreciation, which offer a more detailed analysis on the attitudes present in the articles. The sociocognitive approach, additionally, offers a way of analyzing a more broad context affecting the articles. The findings were then compared, to see if there are differences between the articles, or between the news sites with alleged bias. The findings showed that CNN, with alleged Democratic bias, had a more symphatetic attitude towards income inequality, whereas Fox News, with more Republican views, showed clearly less concern towards the issue. Moreover, the Fox News articles had such dubious claims that the underlying ideology behind the articles could be even supporting of income inequality, as it allows the rich to pursue all the wealth they can without having to give anything away. The results, thus, suggest that the political ideologies may a significant effect on media discourse, which, in turn, may have a significant effect on the attitudes of the public towards great issues that could require prompt measures.