Incorporating Semantic Awareness and Personalization into Microblog Search

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


PhD Thesis Defence

Title: "Incorporating Semantic Awareness and Personalization into Microblog 
Search"

By

Mr. Jan VOSECKY


Abstract

In recent years, microblogging services, such as Twitter, emerged as a popular 
platform for real-time information exchange among millions of users. However, 
the vast amount of content results in an information overload when searching in 
microblogs. Given the user's search query, delivering relevant content is a 
challenging problem. In this thesis, we therefore present three complementary 
approaches to tackle the challenges of microblog search.

First, we propose a method to determine the quality of microblog documents 
(called "tweets"). To model the quality of tweets, we devise a set of 
link-based features, in addition to content-based features. Novel metrics are 
proposed to reflect quality-based reputation of websites, hashtags and users.

Second, we present two frameworks to model topics discussed in microblogs. In 
our Multi-faceted Topic Modeling framework, we tackle both the short length of 
tweets and the rich semantics discussed by microblog users. We first perform 
semantic enrichment to inject additional semantics into the short tweets. We 
then model latent topics that comprise the social terms in Twitter, auxiliary 
terms from external URLs and named entities. In our Geographic Twitter Topic 
Modeling framework, we focus on spatial aspects of microblog topics. We propose 
a content-based method for extracting locations from tweets and model the rich 
interplay between microblog topics and locations.

Third, we present a framework for Collaborative Personalized Twitter Search. 
Traditional techniques for personalized Web search are insufficient in the 
microblog domain, because of the diversity of topics, sparseness of user data 
and the highly social nature. Our framework introduces a topic-aware user model 
structure to manage topical diversity. We then develop a collaborative user 
model, which exploits the user's social connections to obtain a comprehensive 
account of her preferences. A detailed evaluation has demonstrated a superior 
ranking performance of our framework compared with state-of-the-art baselines.


Date:			Monday, 16 February 2015

Time:			2:30pm - 4:30pm

Venue:			Room 3494
 			Lifts 25/26

Chairman:		Prof. VAN DER LANS Ralf (MARK)

Committee Members:	Prof. Wilfred Ng (Supervisor)
 			Prof. Dik-Lun Lee
 			Prof. Nevin Zhang
 			Prof. Prasanna Karhade (ISOM)
 			Prof. Jeffrey Yu (Sys. Eng., & Eng. Mgmt., CUHK)


**** ALL are Welcome ****