Publication Type

Conference Proceeding Article

Publication Date

6-2014

Abstract

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.

Keywords

brand preference, topic model, item adoption

Discipline

Computer Sciences | Databases and Information Systems

Research Areas

Data Management and Analytics

Publication

Proceedings of the Eight International Conference on Weblog and Social Media: 1-4 June 2014, Ann Arbor, Michigan

First Page

325

Last Page

334

ISBN

9781577356592

Publisher

AAAI Press

City or Country

Palo Alto, CA

Additional URL

http://www.aaai.org/ocs/index.php/ICWSM/ICWSM14/paper/view/8082

Share

COinS