Exploring the power of supervised learning methods for company name disambiguation in microblog posts

Abstract

Entity disambiguation is the task of identifying the real world entity that was referred to/mentioned in a context. Ambiguous references to entities may occur due to variations of how an entity is referenced (BT, British Telecom) or inherent ambiguities of the names used for entities (Orange Telecom vs. fruit orange), and misspellings (Best Buy vs. BestBuy). Ambiguities in company names however come with a price, when it comes to nding information about the company on the Web. Recently, tracking social media for brand management has become a very important part of the process in marketing, public relations, and product marketing. Therefore, resolving references to real world objects has become an important part of social media analytics systems. In this thesis, we study di erent machine learning algorithms for entity disambiguation in micro-blogging posts. We show that with the carefully selected set of features, supervised learning techniques would improve the disambiguation quality signi cantly.