Sentiment Analysis with Incremental Human-in-the-Loop Learning and Lexical Resource Customization

Mishra, Shubhanshu; Diesner, Jana; Byrne, Jason; Surbeck, Elizabeth

Permalink

https://hdl.handle.net/2142/79517 Copy

Description

Title

Sentiment Analysis with Incremental Human-in-the-Loop Learning and Lexical Resource Customization

Author(s)

• Mishra, Shubhanshu
• Diesner, Jana
• Byrne, Jason
• Surbeck, Elizabeth

Contributor(s)

• Tao, Liang
• Chin, Chieh-Le

Issue Date

2015-09-04

Keyword(s)

• Text analysis
• Natural Language Processing
• Online Learning
• Software

Abstract

The adjustment of probabilistic models for sentiment analysis to changes in language use and the perception of products can be realized via incremental learning techniques. We provide a free, open and GUI-based sentiment analysis tool that allows for a) relabeling predictions and/or adding labeled instances to retrain the weights of a given model, and b) customizing lexical resources to account for false positives and false negatives in sentiment lexicons. Our results show that incrementally updating a model with information from new and labeled instances can substantially increase accuracy. The provided solution can be particularly helpful for gradually refining or enhancing models in an easily accessible fashion while avoiding a) the costs for training a new model from scratch and b) the deterioration of prediction accuracy over time.

Publisher

ACM Digital Library

Type of Resource

text

Language

en

Permalink

http://hdl.handle.net/2142/79517

DOI

https://doi.org/10.1145/2700171.2791022

Sponsor(s)/Grant Number(s)

Anheuser-Busch InBev

Owning Collections