LAUSR

The opportunity to capture the opinions of the general public has raised growing interest both within the scientific community, leading to many exciting open challenges, and in the business world due to the remarkable range of benefits envisaged, including from marketing, business intelligence and financial prediction. Mining opinions and sentiments from natural language, however, is an extremely difficult task as it involves a deep understanding of most of the explicit and implicit, regular and irregular, syntactical and semantic rules appropriate of a language. Existing approaches to sentiment analysis mainly rely on parts of text in which opinions are explicitly expressed such as polarity terms, affect words, and their co-occurrence frequencies. However, opinions and sentiments are often conveyed implicitly through latent semantics, which make purely syntactical approaches ineffective. Concept-level approaches, instead, leverage knowledge representation and reasoning techniques to accomplish semantic text analysis. This helps the system grasp the conceptual and affective information associated with natural language opinions. By relying on large semantic knowledge bases, such approaches step away from blindly using keywords and word co-occurrence counts and instead rely on the implicit features associated with natural language concepts. Superior to purely syntactical techniques, concept-based approaches can detect subtly expressed sentiments. Conceptbased approaches, in fact, can analyze multi-word expressions that do not explicitly convey emotion, but are related to concepts that do so.