TY - JOUR
T1 - Analyzing firm-specific social media and market
T2 - A stakeholder-based event analysis framework
AU - Jiang, Shan
AU - Chen, Hsinchun
AU - Nunamaker, Jay F.
AU - Zimbra, David
N1 - Funding Information:
The research is based upon the work supported in part by the National Science Foundation under Grant No. CBET-0730908 and by the Defense Threat Reduction Agency under Award No. HDTRA1-09-1-0058 . Thanks to Cathy Larson for her suggestions and comments.
Publisher Copyright:
© 2014 Elsevier B.V. All rights reserved.
PY - 2014/11
Y1 - 2014/11
N2 - Discussion content in firm-specific social media helps managers understand stakeholders' concerns and make informed decisions. Despite such benefits, the over-abundance of information online makes it difficult to identify and focus on the most important stakeholder groups. In this study, we propose a novel stakeholder-based event analysis framework that uses online stylometric analysis to segment the forum participants by stakeholder groups, and partitions their messages into different time periods of major firm events to examine how important stakeholders evolve over time. With this approach, we identified stakeholder groups from a sample of six companies in the petrochemical and banking industries, using more than 500,000 online message postings. To evaluate the proposed system, we conducted market prediction within the identified groups, and compared the prediction performance with traditional approaches that did not account for stakeholder groups or events. Results showed that some stakeholder groups identified by our system had stronger relationships with firms' market performance, compared to the entire set of web forum participants. Incorporating event-induced temporal dynamics further improved the prediction performance.
AB - Discussion content in firm-specific social media helps managers understand stakeholders' concerns and make informed decisions. Despite such benefits, the over-abundance of information online makes it difficult to identify and focus on the most important stakeholder groups. In this study, we propose a novel stakeholder-based event analysis framework that uses online stylometric analysis to segment the forum participants by stakeholder groups, and partitions their messages into different time periods of major firm events to examine how important stakeholders evolve over time. With this approach, we identified stakeholder groups from a sample of six companies in the petrochemical and banking industries, using more than 500,000 online message postings. To evaluate the proposed system, we conducted market prediction within the identified groups, and compared the prediction performance with traditional approaches that did not account for stakeholder groups or events. Results showed that some stakeholder groups identified by our system had stronger relationships with firms' market performance, compared to the entire set of web forum participants. Incorporating event-induced temporal dynamics further improved the prediction performance.
KW - Community identification
KW - Market prediction
KW - Social media
KW - Stakeholder
UR - http://www.scopus.com/inward/record.url?scp=85027931402&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85027931402&partnerID=8YFLogxK
U2 - 10.1016/j.dss.2014.08.001
DO - 10.1016/j.dss.2014.08.001
M3 - Article
AN - SCOPUS:85027931402
VL - 67
SP - 30
EP - 39
JO - Decision Support Systems
JF - Decision Support Systems
SN - 0167-9236
ER -