research data . Dataset . 2017

Dataset: input and results related to the paper 'Anticipointment detection in event tweets'

Kunneman, F.A.; Mulken, M.J.P. Van; Bosch, A.P.J. Van Den;
Open Access
  • Published: 01 Jan 2017
  • Publisher: DANS EASY
  • Country: Netherlands
Abstract
This dataset features the training models, emotion classifications and emotion patterns before and after events, related to the paper: F. Kunneman, M. van Mulken and A. Van den Bosch, Anticipointment detection in event tweets (under review) Abstract of the study: We developed a system to detect positive expectation, disappointment, and satisfaction in tweets that refer to events automatically discovered in the Twitter stream. The emotional content shared on Twitter when referring to public events can provide insights into the presumed and experienced quality of the event. We expected to find a connection between positive expectation and disappointment, a succession that is sometimes referred to as anticipointment. The application of computational approaches makes it possible to detect the presence and strength of this hypothetical relation for a large number of events. We extracted events from a longitudinal data set of Dutch Twitter posts, and modeled classifiers to recognize emotion in the tweets related to those events by means of hashtag-labeled training data. After classifying all tweets before and after the events in our data set, we summarized the collective emotions by calculating the percentage of tweets classified with an emotion as well as ranking tweets based on the classifier confidence score for an emotion and selecting the 90th percentile. Only a weak correlation of around 0.2 was found between positive expectation and disappointment, while a higher correlation of 0.6 was found between positive expectation and satisfaction. The most anticipointing events were events with a clear loss, such as a canceled event or when the favored sports team had lost. We conclude that senders of Twitter posts might be more inclined to share satisfaction than disappointment after a much anticipated event. Subject period: January 1st 2011 until October 31st 2015
Persistent Identifiers
Subjects
free text keywords: Twitter, Emotion, Emotion detection, Machine learning, Natural Language Processing, Event detection, Twitter; Emotion; Emotion detection; Machine learning; Natural Language Processing; Event detection, Computer science, Language and literature studies, Communication sciences, Temporal coverage: start=2011-01-01; end=2015-10-31 (subject period)
Communities
  • Digital Humanities and Cultural Heritage
1 research outcomes, page 1 of 1
Any information missing or wrong?Report an Issue