Work

A Conceptual Framework for Inferring Implicatures

Year: 2014

Type: conference-paper

Abstract: While previous sentiment analysis research has concentrated on the interpretation of explicitly stated opinions and attitudes, this work addresses a type of opinion implicature (i.e., opinion-oriented default inference) in real-world text.This work describes a rule-based conceptual framework for representing and analyzing opinion implicatures.In the course of understanding implicatures, the system recognizes implicit sentiments (and beliefs) toward various events and entities in the sentence, often of mixed polarities; thus, it produces a richer interpretation than is typical in opinion analysis.

Source: Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA)

DOI: 10.3115/v1/w14-2625

Authors: Janyce Wiebe, Lingjia Deng

Institution: University of Pittsburgh

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, Defense Advanced Research Projects Agency

Awards: RI: Small: Collaborative Research: Word Sense and Multilingual Subjectivity Analysis, G2778423969