Files in this item

FilesDescriptionFormat

application/pdf

application/pdfPoster_HT_jd08172015.pdf (906kB)
Poster PDFPDF

application/vnd.openxmlformats-officedocument.presentationml.presentation

application/vnd.openxmlformats-officedocument.presentationml.presentationPoster_HT_jd08172015.pptx (1MB)
Poster PPTMicrosoft PowerPoint 2007

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-Li
Subject(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.
Issue Date:2015-09-04
Publisher:ACM Digital Library
Citation Info:Mishra, Shubhanshu, Jana Diesner, Jason Byrne, and Elizabeth Surbeck. "Sentiment Analysis with Incremental Human-in-the-Loop Learning and Lexical Resource Customization." In Proceedings of the 26th ACM Conference on Hypertext & Social Media, pp. 323-325. ACM, 2015.
Genre:Conference Poster
Type:Text
Language:English
URI:http://hdl.handle.net/2142/79517
DOI:10.1145/2700171.2791022
Sponsor:Anheuser-Busch InBev
Date Available in IDEALS:2015-09-11


This item appears in the following Collection(s)

Item Statistics