oIQa: An Opinion Influence Oriented Question Answering Framework with Applications to Marketing Domain

2017-09-01RANLP 2017Unverified0· sign in to hype

Dumitru-Clementin Cercel, Cristian Onose, Stefan Trausan-Matu, Florin Pop

Unverified — Be the first to reproduce this paper.

Abstract

Understanding questions and answers in QA system is a major challenge in the domain of natural language processing. In this paper, we present a question answering system that influences the human opinions in a conversation. The opinion words are quantified by using a lexicon-based method. We apply Latent Semantic Analysis and the cosine similarity measure between candidate answers and each question to infer the answer of the chatbot.

Tasks

Chatbot Information Retrieval Marketing Opinion Mining Question Answering Sentiment Analysis

oIQa: An Opinion Influence Oriented Question Answering Framework with Applications to Marketing Domain

Abstract

Tasks

Reproductions