Online social networks (OSNs) have become an integral part of our everyday lives, where we share our thoughts and feelings. This study analyses the extent to which the changes of an individual's real-world psychological mood can be inferred by tracking their online activity on Facebook and Twitter. By capturing activities from the OSNs and ground truth data via experience sampling, it was found that mood changes can be detected within a window of 7 days for 61% of the participants by using specific, combined online activity signals. The participants fall into three distinct groups: Those whose mood correlates positively with their online activity, those who correlate negatively and those who display a weak correlation. We trained two classifiers to identify these groups using features from their online activity, which achieved precision of 95.2% and 84.4% respectively. Our results suggest that real-world mood changes can be passively tracked through online activity on OSNs.
|Title of host publication||UbiComp 2016 Adjunct - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||9|
|Publication status||Published (in print/issue) - 12 Sept 2016|
|Event||2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016 - Heidelberg, Germany|
Duration: 12 Sept 2016 → 16 Sept 2016
|Conference||2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016|
|Period||12/09/16 → 16/09/16|
- Online Social Networks
- Sentiment Analysis.
- Social Psychology