Generating, Refining and Using Sentiment Lexicons

In this chapter, which is based on [7–9], we report on work on the generation, refinement and use of sentiment lexicons that was carried out within the DuOMAn project. The project was focused on the development of language technology to support online media analysis. In the area of media analysis, one of the key tasks is collecting detailed information about opinions and attitudes toward specific topics from various sources, both offline (traditional newspapers, archives) and online (news sites, blogs, forums). Specifically, media analysis concerns the following system task: given a topic and list of documents (discussing the topic), find all instances of attitudes toward the topic (e.g., positive/negative sentiments, or, if the topic is an organisation or person, support/criticism of this entity). For every such instance, one should identify the source of the sentiment, the polarity and, possibly, subtopics that this attitude relates to (e.g., specific targets of criticism or support). Subsequently, a (human) media analyst must be able to aggregate the extracted information by source, polarity or subtopics, allowing him to build support/criticism networks etc. [1]. Recent advances in language technology, especially in sentiment analysis, promise to (partially) automate this task. Sentiment analysis is often considered in the context of the following two tasks: