Estimating the time between twitter messages and future events

Ali Hürriyetoʇlu, Florian Kunneman, Antal Van Den Bosch

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

We describe and test three methods to estimate the remain-ing time between a series of microtexts (tweets) and the future event they refer to via a hashtag. Our system gener-ates hourly forecasts. A linear and a local regression-based approach are applied to map hourly clusters of tweets directly onto time-to-event. To take changes over time into account, we develop a novel time series analysis approach that first derives word frequency time series from sets of tweets and then performs local regression to predict time- to-event from nearest-neighbor time series. We train and test on a single type of event, Dutch premier league foot- ball matches. Our results indicate that in an 'early' stage, four days or more before the event, the time series analysis produces time-to-event predictions that are about one day off; closer to the event, local regression attains a similar ac-curacy. Local regression also outperforms both mean and median-based baselines, but on average none of the tested system has a consistently strong performance through time.

Original languageEnglish
Title of host publication13th Dutch-Belgian Workshop on Information Retrieval, DIR 2013
Pages20-23
Number of pages4
Volume986
Publication statusPublished - 1 Jan 2013
Externally publishedYes
Event13th Dutch-Belgian Workshop on Information Retrieval, DIR 2013 - Delft, Netherlands
Duration: 26 Apr 2013 → …

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR Workshop Proceedings
ISSN (Print)1613-0073

Conference

Conference13th Dutch-Belgian Workshop on Information Retrieval, DIR 2013
CountryNetherlands
CityDelft
Period26/04/13 → …

Keywords

  • Event prediction
  • Time series analysis
  • Twitter

Fingerprint Dive into the research topics of 'Estimating the time between twitter messages and future events'. Together they form a unique fingerprint.

  • Cite this

    Hürriyetoʇlu, A., Kunneman, F., & Van Den Bosch, A. (2013). Estimating the time between twitter messages and future events. In 13th Dutch-Belgian Workshop on Information Retrieval, DIR 2013 (Vol. 986, pp. 20-23). (CEUR Workshop Proceedings).