Skip to main navigation Skip to search Skip to main content

Combining Heterogeneous User Generated Data to Sense Well-being

  • A. Tsakalidis
  • , M. Liakata
  • , T. Damoulas
  • , B. Jellinek
  • , W. Guo
  • , A.I. Cristea
  • University of Warwick

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

Abstract

In this paper we address a new problem of predicting affect and well-being scales in a real-world setting of heterogeneous, longitudinal and non-synchronous textual as well as non-linguistic data that can be harvested from on-line media and mobile phones. We describe the method for collecting the heterogeneous longitudinal data, how features are extracted to address missing information and differences in temporal alignment, and how the latter are combined to yield promising predictions of affect and well-being on the basis of widely used psychological scales. We achieve a coefficient of determination (R2) of 0.71-0.76 and a ρ of 0.68-0.87 which is higher than the state-of-the art in equivalent multi-modal tasks for affect. © 1963-2018 ACL.
Original languageEnglish
Title of host publicationProceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
PublisherThe COLING 2016 Organizing Committee
Pages3007-3018
Number of pages12
ISBN (Print)978-4-87974-704-4
Publication statusPublished - 2016
Event26th International Conference on Computational Linguistics, COLING 2016 - Osaka, Japan
Duration: 11 Dec 201616 Dec 2016
https://coling2016.anlp.jp/

Conference

Conference26th International Conference on Computational Linguistics, COLING 2016
Abbreviated titleCOLING 2016
Country/TerritoryJapan
CityOsaka
Period11/12/1616/12/16
Internet address

Keywords

  • A-coefficient
  • Heterogeneous users
  • Linguistic data
  • Longitudinal data
  • Missing information
  • Real world setting
  • State of the art
  • Temporal alignment
  • Computational linguistics

Fingerprint

Dive into the research topics of 'Combining Heterogeneous User Generated Data to Sense Well-being'. Together they form a unique fingerprint.

Cite this