Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 1, 2019

Term Weighting for Feature Extraction on Twitter: A Comparison Between BM25 and TF-IDF

View Full Paper
Ask AI
Bookmark
Share

Authors

AKAmmar Ismael Kadhim

Discussion

Loading...

Member takes

Overview

Comparative evaluation of BM25 and TF-IDF for feature extraction in Twitter text classification, suggesting TF-IDF is more effective.

Key Points

  • The aim is to compare the effectiveness of BM25 and TF-IDF in feature extraction for text classification on Twitter.
  • Two feature extraction techniques, BM25 and TF-IDF, were evaluated for term weighting on Twitter data.
  • Performance was measured using the F1-measure to assess classification effectiveness.
  • TF-IDF achieved an F1-measure of 89.77, surpassing the 89.16 achieved by BM25.
  • The results suggest TF-IDF is preferred for efficient feature extraction in text classification tasks on Twitter.

Cite This Study

Ammar Ismael Kadhim (2019) studied this question.

synapsesocial.com/papers/6a080370686e45fdbcfe1119https://doi.org/10.1109/icoase.2019.8723825
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1From TF-IDF to BM25: Foundations of Term Weighting and Implications for Modern Information Retrieval Systems2026
  2. 2Enhancing machine learning-based sentiment analysis through feature extraction techniques2024 · 23 citations
  3. 3Mental Health Detection with TF-IDF Feature Extraction2024 · 1 citations
  4. 4Comparative Study among Term Frequency-Inverse Document Frequency and Count Vectorizer towards K Nearest Neighbor and Decision Tree Classifiers for Text Dataset2024 · 2 citations
  5. 5An Efficient Feature Selection with an Enhanced Supervised Term-Weighting Scheme in Multi-Class Text Classification2026