|Title||Sentiment Classification: Linguistic and Non-linguistic Issues|
|Publication Type||Conference Paper|
|Year of Publication||2005|
|Conference Name||Israeli Seminar on Computational Linguistics|
|Conference Location||Technion, Haifa, Israel|
There is a growing interest in the NLP community in methods for determining the sentiment (tone, polarity, semantic orientation) of a given piece of text (see references below). The large number of potential applications, such as quantitative summarization of customer reviews, public opinion surveys, business intelligence, trend analysis, etc.justifies this. From a research point of view, sentiment classification is an interesting
A related task is extraction of representative phrases, to be used as quotes in a summary, supporting the sentiment evaluation of a review. Quotes of interest may be generally positive or negative, or pertain to a specific dimension (topic) of the subject domain.
In this presentation, I will describe the common approaches to tackle this challenge and will suggest directions that I believe to be the most appropriate. I will discuss the contribution of various levels of linguistic analysis to the effectiveness of the classification method.