Overcoming Vocabulary Limitations in Twitter Microblogs

Abstract

One major di culty in performing ad-hoc search on microblogs such as Twitter is the limited vocabulary of each document due their short length. In this paper, two approaches to addressing this issue are presented. The rst is query expansion through pseudo-relevance feedback and the other is document expansion of tweets using web documents linked from the body of the tweet. Tweets are expanded by concatenating the contents of the title tag and the meta descriptor tags of the document to the tweet itself. These two approaches gave additive gains in MAP and Precision at 30.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2012
Accession Number
ADA576841

Entities

People

  • Jamie Callan
  • Reyyan Yeniterzi
  • Yubin Kim

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Additives (Chemicals)
  • Algorithms
  • Data Processing
  • Detection
  • Feedback
  • Information Science
  • Language
  • Natural Language Processing
  • Online Communications
  • Personality
  • Precision
  • Social Media
  • Standards
  • Statistics
  • Vocabulary
  • Words (Language)

Fields of Study

  • Computer science

Readers

  • Information Retrieval
  • Library and Information Science
  • Systems Analysis and Design