Tweetin' in the rain: exploring societal-scale effects of weather on mood

From Brede Wiki

Jump to: navigation, search
Conference paper (help)
Tweetin' in the rain: exploring societal-scale effects of weather on mood
Authors: Aniko Hannak, Eric Anderson, Lisa Feldman Barrett, Sune Lehmann, Alan Mislove, Mirek Riedewald
Citation: Proceedings of the Sixth International AAAI Conference on Weblogs and Social Media  : 479-482. 2012
Editors:
Publisher: Association for the Advancement of Artificial Intelligence
Meeting: 6th International AAAI Conference on Weblogs and Social Media
Database(s): Google Scholar cites
DOI: Define doi.
Link(s): http://www.ccs.neu.edu/home/amislove/publications/Weather-ICWSM.pdf
Search
Web: DuckDuckGo Bing Google Yahoo!Google PDF
Article: Google Scholar PubMed
Restricted: DTU Digital Library
Services
Format: BibTeX

Tweetin' in the rain: exploring societal-scale effects of weather on mood describes a study on mood based on sentiment analysis of Twitter postings and weather data.

They show a plot on the predicted sentiment as a function of humidity and temperature.

Contents

[edit] Data

Twitter data from 2006-2009 from 54,981,152 accounts and a total of 1,516,115,233 tweets, see also[1] They reduced the dataset to 90.3% 1,369,833,417 tweets

[edit] Methodology

They based their text sentiment analysis on a emoticon labels and cites J. Read.[2] They tested this approach against Mislove-1000 Amazon Mechanical Turk labeled tweets.

[edit] Related papers

  1. Circadian patterns of Wikipedia editorial activity: a demographic analysis
  2. Large-scale sentiment analysis for news and blogs
  3. Temporal patterns of happiness and information in a global social network: hedonometrics and Twitter
  4. Using emoticons to reduce dependency in machine learning techniques for sentiment classification

[edit] References

  1. Measuring user influence in Twitter: the million follower fallacy
  2. Using emoticons to reduce dependency in machine learning techniques for sentiment classification
Personal tools