Skip to main content

Research Repository

Advanced Search

Combining heterogeneous user generated data to sense well-being

Tsakalidis, Adam; Liakata, Maria; Damoulas, Theodoros; Jellinek, Brigitte; Guo, Weisi; Cristea, A.I.

Combining heterogeneous user generated data to sense well-being Thumbnail


Authors

Adam Tsakalidis

Maria Liakata

Theodoros Damoulas

Brigitte Jellinek

Weisi Guo



Contributors

Yuji Matsumoto
Editor

Rashmi Prasad
Editor

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.

Citation

Tsakalidis, A., Liakata, M., Damoulas, T., Jellinek, B., Guo, W., & Cristea, A. (2016). Combining heterogeneous user generated data to sense well-being. In Y. Matsumoto, & R. Prasad (Eds.), Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics : Technical Papers (3007-3018)

Conference Name COLING 2016
Conference Location Osaka
Acceptance Date Sep 21, 2016
Online Publication Date Dec 1, 2016
Publication Date Dec 1, 2016
Deposit Date Jul 11, 2018
Publicly Available Date Jul 31, 2018
Pages 3007-3018
Book Title Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics : Technical Papers.
Public URL https://durham-repository.worktribe.com/output/1144363
Publisher URL http://coling2016.anlp.jp/
Related Public URLs http://wrap.warwick.ac.uk/81828/

Files







You might also like



Downloadable Citations