Research map / Learning theory and algorithms / Combinatorial and search optimization
Identifying Search Keywords for Finding Relevant Social Media Posts
Shuai Wang, Zhiyuan Chen, Bing Liu, Sherry Emery
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add re-ranking by searching each candidate (DR Iter-1) over entropy-only initial ranking (ablation) | Double Ranking · E-Cig keywords | Precision@n: 0.00 -> 0.20 (P@5, ENT -> DR Iter-1) | Improved |
| add re-ranking step to entropy initial ranking (ablation) | Entropy ranking · Cigar keywords | Precision@n: 0.20 -> 1.00 (P@5) | Improved |
| run second iteration with discovered keywords added (ablation) | DR · E-Cig keywords | Precision@n: 0.20 -> 1.00 (P@5) | Improved |
| run second iteration with discovered keywords added (ablation) | DR · Blunt keywords | Precision@n: 0.40 -> 0.60 (P@5) | Improved |
| run second iteration with discovered keywords added (ablation) | DR · Cigar keywords | Precision@n: 1.00 -> 0.40 (P@5) | Hurt |
| run second iteration with discovered keywords added (ablation) | DR · Grimm keywords | Precision@n: 0.80 -> 0.40 (P@5) | Hurt |
| run second iteration with discovered keywords added (ablation) | DR · Whispers keywords | Precision@n: 0.40 -> 0.20 (P@5) | Hurt |
| use entropy against random reference tweets instead of raw term frequency (ablation) | initial ranking · Cigar keywords | Precision@n: 0.00 -> 0.20 (P@5, TF -> ENT) | Improved |
| second iteration on relevant-word precision (ablation) | DR · E-Cig relevant words | Precision@n: 0.60 -> 0.75 (P@20, Iter-1 -> Iter-2) | Improved |
| second iteration on relevant-word precision (ablation) | DR · Whispers relevant words | Precision@n: 0.65 -> 0.30 (P@20) | Hurt |
Closest papers by meaning
- Twitter Summarization Based on Social Network and Sparse Reconstruction (AAAI 2018 · similarity 0.80)
- Segmentation of Tweets with URLs and its Applications to Sentiment Analysis (AAAI 2021 · similarity 0.80)
- Microsummarization of Online Reviews: An Experimental Study (AAAI 2016 · similarity 0.79)
- SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services (ICML 2025 · similarity 0.77)
- SMTPD: A New Benchmark for Temporal Prediction of Social Media Popularity (CVPR 2025 · similarity 0.77)
- C-SEO Bench: Does Conversational SEO Work? (NeurIPS 2025 · similarity 0.77)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
