Extracting sentiment as a function of discourse structure and topicality

Abstract

We present an approach to extracting sentiment from texts that makes use of con- textual information. Using two dierent approaches, we extract the most relevant sentences of a text, and calculate semantic orientation weighing those more heavily. The …rst approach makes use of discourse structure via Rhetorical Structure Theory, and extracts nuclei as the relevant parts; the second approach uses a topic classi…er built using support vector machines, which extracts topic sentences from texts. The use of weights on relevant sentences shows an improvement over word-based methods that consider the entire text equally. In the paper, we also describe an enhancement of our previous word-based methods in the treatment of intensi…ers and negation, and the addition of other parts of speech beyond adjectives.