You are here


Information extraction and mining aims to analyze raw information to extract relevant and structured information in order to foster the detection of specific knowledge.


Opinion Mining and Sentiment Analysis are natural language processing tasks which aims at (i) detecting the presence of opinions within a resource and (ii) classifying this resource according to the opinion they express about a given subject.

Generally speaking, opinion mining and sentiment analysis aim at determining the attitude of a speaker or a writer with respect to a topic or the overall tonality of a document. In the recent years, the exponential increase in the use of the Web for exchanging public opinions about events, facts, products, etc. led to an extensive usage of opinion mining and sentiment analysis approaches, especially for marketing and social purposes.

Given a document collection, Information Retrieval is the task of returning the most relevant documents for a specified user query.
Approaches in this field aim to improve information retrieval performances by exploiting knowledge extraction techniques.
Query and documents are expanded with semantic terms obtained by processing them with Natural Language Processing methods (e.g., Entity Linking, Frame Detection), and by linking them to available Semantic Web and Linked Open Data knowledge bases (e.g., DBpedia, YAGO).


Multi-Domain Fuzzy Sentiment Analyzer Demo:
Tool (version 2.25) [Download]
Property file (to be deployed in the same folder of the .jar executable [Download]
Results on the complete version of the Blitzer dataset (Elementary Task) [Download]