TY - GEN
T1 - Unsupervised event tracking by integrating twitter and instagram
AU - Wang, Shiguang
AU - Giridhar, Prasanna
AU - Kaplan, Lance
AU - Abdelzaher, Tarek
N1 - Publisher Copyright:
© 2017 ACM.
PY - 2017/4/18
Y1 - 2017/4/18
N2 - This paper proposes an unsupervised framework for tracking real world events from their traces on Twitter and Instagram. Empirical data suggests that event detection from Instagram streams errs on the false-negative side due to the relative sparsity of Instagram data (compared to Twitter data), whereas event detection from Twitter can sutter from false-positives, at least if not paired with careful analysis of tweet content. To tackle both problems simultaneously, we design a unified unsupervised algorithm that fuses events detected originally on Instagram (called I-events) and events detected originally on Twitter (called T-events), that occur in adjacent periods, in an attempt to combine the benefits of both sources while eliminating their individual disadvantages. We evaluate the proposed framework with real data crawled from Twitter and Instagram. The results indicate that our algorithm significantly improves tracking accuracy compared to baselines.
AB - This paper proposes an unsupervised framework for tracking real world events from their traces on Twitter and Instagram. Empirical data suggests that event detection from Instagram streams errs on the false-negative side due to the relative sparsity of Instagram data (compared to Twitter data), whereas event detection from Twitter can sutter from false-positives, at least if not paired with careful analysis of tweet content. To tackle both problems simultaneously, we design a unified unsupervised algorithm that fuses events detected originally on Instagram (called I-events) and events detected originally on Twitter (called T-events), that occur in adjacent periods, in an attempt to combine the benefits of both sources while eliminating their individual disadvantages. We evaluate the proposed framework with real data crawled from Twitter and Instagram. The results indicate that our algorithm significantly improves tracking accuracy compared to baselines.
UR - http://www.scopus.com/inward/record.url?scp=85019031689&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85019031689&partnerID=8YFLogxK
U2 - 10.1145/3055601.3055615
DO - 10.1145/3055601.3055615
M3 - Conference contribution
AN - SCOPUS:85019031689
T3 - Proceedings - 2017 2nd International Workshop on Social Sensing, SocialSens 2017 (part of CPS Week)
SP - 81
EP - 86
BT - Proceedings - 2017 2nd International Workshop on Social Sensing, SocialSens 2017 (part of CPS Week)
PB - Association for Computing Machinery, Inc
T2 - 2nd International Workshop on Social Sensing, SocialSens 2017
Y2 - 21 April 2017
ER -