Webis: an ensemble for Twitter sentiment detection

From Brede Wiki
Jump to: navigation, search
Conference paper (help)
Webis: an ensemble for Twitter sentiment detection
Authors: Matthias Hagen, Martin Potthast, Michel Büchner, Benno Stein
Citation: Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)  : 582-589. 2015 June
Publisher: Association for Computational Linguistics
Meeting: SemEval 2015
DOI: Define doi.
Link(s): http://alt.qcri.org/semeval2015/cdrom/pdf/SemEval097.pdf
Web: DuckDuckGo Bing Google Yahoo!Google PDF
Article: Google Scholar PubMed
Restricted: DTU Digital Library
Format: BibTeX

Webis: an ensemble for Twitter sentiment detection describes a reimplementation of state-of-the-art method for Twitter sentiment analysis.

Reimplemented methods:

  1. NRC-Canada (2013): Emotions evoked by common words and phrases: Using mechanical turk to create an emotion lexicon
  2. GU-MLT-LT (2013): Sentiment analysis of short messages using linguistic features and stochastic gradient descent
  3. KLUE (2013): KLUE: simple and robust methods for polarity classification
  4. TeamX (2014): Teamx: a sentiment analyzer with enhanced lexicon mapping and weighting scheme for unbalanced data

The method showed superior performance in SemEval 2015 ("rank 1 among 40 systems")

Personal tools