2018
NAACL
NAACL 2018
DebugSL: An Interactive Tool for Debugging Sentiment Lexicons
Abstract
AbstractWe introduce DebugSL, a visual (Web) debugging tool for sentiment lexicons (SLs). Its core component implements our algorithms for the automatic detection of polarity inconsistencies in SLs. An inconsistency is a set of words and/or word-senses whose polarity assignments cannot all be simultaneously satisfied. DebugSL finds inconsistencies of small sizes in SLs and has a rich user interface which helps users in the correction process. The project source code is available at https://github.com/atschneid/DebugSL A screencast of DebugSL can be viewed at https://cis.temple.edu/~edragut/DebugSL.webm
🧭
Keyword Pioneer
— polarity inconsistency
🐝
Cross-Pollinator
— Artificial Intelligence, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Natural Language Processing, Speech & Audio