Imputing Missing Social Media Data Stream in Multisensor Studies of Human Behavior

Saha, K and Mulukutla, R and Nies, K and Granda, R P and Sirigiri, A and Yoo, D W and Audia, P and Campbell, A T and Chawla, N V and D'Mello, S K and Dey, A K and Reddy, M D and Jiang, K and Liu, Q and Mark, G and Moskal, E and Striegel, A and Choudhury, D M and Swain, D V and Gregg, J M and Grover, T and Lin, S and Martinez, G J and Mattingly, S M and Mirjafari, S (2019) Imputing Missing Social Media Data Stream in Multisensor Studies of Human Behavior. In: 2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII).

Full text not available from this repository. (Request a copy)


The ubiquitous use of social media enables researchers to obtain self-recorded longitudinal data of individuals in real-time. Because this data can be collected in an inexpensive and unobtrusive way at scale, social media has been adopted as a “passive sensor” to study human behavior. However, such research is impacted by the lack of homogeneity in the use of social media, and the engineering challenges in obtaining such data. This paper proposes a statistical framework to leverage the potential of social media in sensing studies of human behavior, while navigating the challenges associated with its sparsity. Our framework is situated in a large-scale in-situ study concerning the passive assessment of psychological constructs of 757 information workers wherein of four sensing streams was deployed - bluetooth beacons, wearable, smartphone, and social media. Our framework includes principled feature transformation and machine learning models that predict latent social media features from the other passive sensors. We demonstrate the efficacy of this imputation framework via a high correlation of 0.78 between actual and imputed social media features. With the imputed features we test and validate predictions on psychological constructs like personality traits and affect. We find that adding the social media data streams, in their imputed form, improves the prediction of these measures. We discuss how our framework can be valuable in multimodal sensing studies that aim to gather comprehensive signals about an individual's state or situation.

Item Type: Conference or Workshop Item (Paper)
Additional Information: The research paper was published by the author with the affiliation of Dartmouth College, Hanover
Subjects: Human Resources Management
Date Deposited: 03 Apr 2021 09:39
Last Modified: 03 Apr 2021 09:39

Actions (login required)

View Item
View Item