Conference Proceeding Article
In marketing and advertising, developing and managingbrands value represent the core activities performedby companies. Successful brands attract buyers andadopters, which in turn increase the companies’ value.Given a set of user-item adoption data, can we inferbrand effects from users adopting items? To answerthis question, we develop the Brand Item Topic Model(BITM) that incorporates users’ brand preferences inthe process of item adoption by the users. We evaluateour model using synthetic and two real world datasetsagainst baseline models which do not consider brand effects.The results show that BITM can determine userswho demonstrate brand preferences and predict itemadoptions more accurately.
brand preference, topic model, item adoption
Computer Sciences | Databases and Information Systems
Data Management and Analytics
Proceedings of the Eight International Conference on Weblog and Social Media: 1-4 June 2014, Ann Arbor, Michigan
City or Country
Palo Alto, CA
LUU, Minh Duc; LIM, Ee Peng; and CHUA, Freddy Chong-Tat.
On Modeling Brand Preferences in Item Adoptions. (2014). Proceedings of the Eight International Conference on Weblog and Social Media: 1-4 June 2014, Ann Arbor, Michigan. 325-334. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/2609
Copyright Owner and License