SENTIMENT ASSESSMENT OF TEXT BY ANALYZING LINGUISTIC FEATURES AND CONTEXTUAL VALENCE ASSIGNMENT
Applied Artificial Intelligence
Emotion Sensitive News Agent (ESNA): A system for user centric emotion sensing from the news
Web Intelligence and Agent Systems
Hi-index | 0.00 |
In this paper, we present a system Affect Sensitive News Agent (ASNA) developed as a news aggregator that fetches news employing several RSS news-feeds and auto-categorizes the news according to affect sensitivity. There are three main factors that distinguish our work from other similar ones. First, we have integrated the approach to sense affective information from news-texts by applying a cognitive theory of emotions known as the OCC model that none have ever considered for news classification. Second, instead of any machine learning algorithm, we used common-sense and current-affairs as our knowledgebase with a rule based approach to assess each line of text by assigning a numerical valence and finally, natural language processing (NLP) technologies are used to perform automated categorization of news stories on the basis of emotional affinity. Relying on these paradigms and content analysis technologies, we have developed a news-browser that can fetch the news from RSS news-feeds and categorizes the theme of the news according to eight emotion-types plus a neutral category for quicker and intuitive understanding.