TY - JOUR
T1 - Finding a needle in the haystack
T2 - Recommending online communities on social media platforms using network and design science
AU - Velichety, Srikar
AU - Ram, Sudha
N1 - Funding Information: Sudha Ram is Anheuser-Busch Chair in MIS, Entrepreneurship, and Innovation and professor of management information systems in the Eller College of Management, University of Arizona. Ram got her PhD from the University of Illinois Urbana-Champaign in 1985. Her research interests are in explainable artificial intelligence, business intelligence and web analytics, social media analytics, enterprise data management, data provenance, and interoperability. She has raised more than 20 million USD worth of grants from several federal agencies including NSF, NIH, GSA, and organizations including IBM, Parkland Center for Clinical Innovation, and the I3FOR Institute. Her research has been published in several top outlets including Management Science, Marketing Science, Management Information Systems Quarterly, Information Systems Research, Journal of Management Information Systems, and Journal of the Association for Information Systems. Publisher Copyright: © 2021, Association for Information Systems. All rights reserved.
PY - 2021
Y1 - 2021
N2 - We address the problem of recommending online communities on social media platforms using design science. Our method is grounded in network science and leverages the random surfer model of the web, small-world networks, strength of weak connections, and connectivity to analyze three types of large-scale networks. In doing so, we design features for structural hole assortativity and local clustering coefficient rank to capture both the diversity and evolution of user interests. We also extract general online community features such as size and overlap. Experiments conducted on a large dataset of 34,000 lists created and subscribed to by 1,600 active Twitter users over a six-month period showed that our network features outperform the general and content features in terms of recommending communities at the top position. In addition, a combination of general and network features generated the best results in the top position with a significant performance improvement over using only the content features. A combination of all three types of features gave the best results in the top-5 and top-10 positions while improving the quality of recommendations at every other position. Our work outperforms the latest work on community recommendations on social media platforms and has major implications for the design of online community recommenders.
AB - We address the problem of recommending online communities on social media platforms using design science. Our method is grounded in network science and leverages the random surfer model of the web, small-world networks, strength of weak connections, and connectivity to analyze three types of large-scale networks. In doing so, we design features for structural hole assortativity and local clustering coefficient rank to capture both the diversity and evolution of user interests. We also extract general online community features such as size and overlap. Experiments conducted on a large dataset of 34,000 lists created and subscribed to by 1,600 active Twitter users over a six-month period showed that our network features outperform the general and content features in terms of recommending communities at the top position. In addition, a combination of general and network features generated the best results in the top position with a significant performance improvement over using only the content features. A combination of all three types of features gave the best results in the top-5 and top-10 positions while improving the quality of recommendations at every other position. Our work outperforms the latest work on community recommendations on social media platforms and has major implications for the design of online community recommenders.
KW - Explainable AI
KW - Network science and design science
KW - Online communities
KW - Recommender systems
KW - Social media platforms
UR - http://www.scopus.com/inward/record.url?scp=85114558033&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85114558033&partnerID=8YFLogxK
U2 - 10.17705/1jais.00694
DO - 10.17705/1jais.00694
M3 - Article
SN - 1558-3457
VL - 22
SP - 1285
EP - 1310
JO - Journal of the Association for Information Systems
JF - Journal of the Association for Information Systems
IS - 5
ER -