Evaluation of peak detection algorithms for social media event detection

  • Philip Healy
  • , Graham Hunt
  • , Steven Kilroy
  • , Theo Lynn
  • , John P. Morrison
  • , Shankar Venkatagiri

Research output: Chapter in Book/Report/Conference proceedingsChapterpeer-review

Abstract

We evaluate the effectiveness of three peak detection algorithms when applied to collection of social media datasets. Each dataset is composed of a year's worth of tweets relating to a topic. The datasets were converted to time series composed of hourly tweet volumes. The objective of the analysis was to identify abnormal surges of communication, which are taken to be representative of the occurrence of events relevant to the topic under consideration. The ground truth was established by manually tagging the time series in order to identify peaks apparent to a human operator. Candidate algorithms were then evaluated in terms of the precision, recall, and F± scores obtained when their output was compared to the manually identified peaks. A general-purpose algorithm is found to perform reasonably well, but seasonality in social media data limits the effectiveness of applying simple algorithms without filtering.

Original languageEnglish
Title of host publicationProceedings - 10th International Workshop on Semantic and Social Media Adaptation and Personalization, SMAP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages55-60
Number of pages6
ISBN (Electronic)9781509002429
DOIs
Publication statusPublished - 31 Dec 2015
Event10th International Workshop on Semantic and Social Media Adaptation and Personalization, SMAP 2015 - Trento, Italy
Duration: 5 Nov 20156 Nov 2015

Publication series

NameProceedings - 10th International Workshop on Semantic and Social Media Adaptation and Personalization, SMAP 2015

Conference

Conference10th International Workshop on Semantic and Social Media Adaptation and Personalization, SMAP 2015
Country/TerritoryItaly
CityTrento
Period5/11/156/11/15

Keywords

  • Analytics
  • Event Detection
  • Peak Detection
  • Social Media
  • Spike Detection
  • Twitter

Fingerprint

Dive into the research topics of 'Evaluation of peak detection algorithms for social media event detection'. Together they form a unique fingerprint.

Cite this