Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!
Get Started for Free

hash_sentiment_huliu

Hu Liu Polarity Lookup Table


Description

A data.table dataset containing an augmented version of Hu & Liu's (2004) positive/negative word list as sentiment lookup values.

Usage

data(hash_sentiment_huliu)

Format

A data frame with 6874 rows and 2 variables

Details

  • x. Words

  • y. Sentiment values (+1, 0, -1.05, -1, -2), -2 indicate phrasing that is always negative (e.g., 'too much fun' and 'too much evil' both denote negative though the following word is positive and negative respectively).

References

Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD-2004). Seattle, Washington.

Hu, M., & Liu, B. (2004). Mining opinion features in customer reviews. National Conference on Artificial Intelligence.

https://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html


lexicon

Lexicons for Text Analysis

v1.2.1
GPL-3
Authors
Tyler Rinker [aut, cre, cph], University of Notre Dame [dtc, cph], Department of Knowledge Technologies [dtc, cph], Unicode, Inc. [dtc, cph], John Higgins [dtc, cph], Grady Ward [dtc], Heiko Possel [dtc], Michal Boleslav Mechura [dtc, cph], Bing Liu [dtc], Minqing Hu [dtc], Saif M. Mohammad [dtc], Peter Turney [dtc], Erik Cambria [dtc], Soujanya Poria [dtc], Rajiv Bajpai [dtc], Bjoern Schuller [dtc], SentiWordNet [dtc, cph], Liang Wu [dtc, cph], Fred Morstatter [dtc, cph], Huan Liu [dtc, cph], Grammar Revolution [dtc, cph], Vidar Holen [dtc, cph], Alejandro U. Alvarez [dtc, cph], Stackoverflow User user2592414 [dtc, cph], BannedWordList.com [dtc, cph], Apache Software Foundation [dtc, cph], Andrew Kachites McCallum [dtc, cph], Alireza Savand [dtc, cph], Zact Anger [dtc, cph], Titus Wormer [dtc, cph], Colin Martindale [dtc, cph], John Wiseman [dtc, cph], Nadra Pencle [dtc, cph], Irina Malaescu [dtc, cph]
Initial release

We don't support your browser anymore

Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.