UWM-HBUT at TREC 2014 Microblog Track: Using Query Expansion (QE) and Event Identification Algorithm (EIA) to Improve Microblog Retrieval Effectiveness
Abstract
This paper reports our contributions and results to TREC 2014 Microblog Track. Different from traditional web pages or database documents, microblogs have their own unique features. Considering sensitivity to time, we introduce a new factor to help to improve tweet retrieval effectiveness. The ranking score of a retrieved tweet is adjusted by considering how close the tweet time stamp is to the event using Event Identification Algorithm (EIA). In addition, we also evaluate the Query Expansion (QE) approach using Google as an external data corpus. There are 55 search topics and the data set contains a total of 243 million tweets provided by the TREC 2014 Microblog Track. Our initial results indicated that QE helped to improve the performance. We also discussed why the EIA approach failed to enhance the retrieval performance.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 2014
- Accession Number
- ADA618592
Entities
People
- Sukjin You
- Wei Huang
- Xiangming Mu
Organizations
- University of Wisconsin–Milwaukee