ISTI at TREC Microblog Track 2012: Real-Time Filtering Through Supervised Learning

Abstract

Our approach to the microblog filtering task is based on learning a relevance classifier from an initial training set of relevant and non relevant tweets, generated by using a simple retrieval method. The classifier is then retrained using the (simulated) user feedback collected during the training process, in order to improve its accuracy as the filtering process goes on. In the official runs the system scored low effectiveness values suffering a strong imbalance toward recall.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 2012
Accession Number
ADA581266

Entities

People

  • Andrea Esuli
  • Diego Marcheggiani
  • Giacomo Berardi

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Algorithms
  • Classification
  • Computer Programs
  • Data Science
  • Feedback
  • Filtration
  • Judgment
  • Language
  • Learning
  • Machine Learning
  • Mobile Phones
  • Online Communications
  • Social Media
  • Supervised Machine Learning
  • Training

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Information Retrieval
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Neural Networks