AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

A Neural Group-wise Sentiment Analysis Model with Data Sparsity Awareness

AAAI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Recommendation representation learning · 9 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 changedWhereMeasuredEffect
Add rating-bias modeling (ablation)NGSAM · Yelp 2013RMSE: 0.7268 -> 0.7163Helped
Add rating-bias modeling (ablation)NGSAM · Yelp 2014RMSE: 0.7099 -> 0.7031Helped
Add rating-bias modeling (ablation)NGSAM · TwitterRMSE: 1.5890 -> 1.5011Helped
Add rating-variance modeling (ablation)NGSAM · Yelp 2013RMSE: 0.7396 -> 0.7163Helped
Add rating-variance modeling (ablation)NGSAM · Yelp 2014RMSE: 0.7211 -> 0.7031Helped
Add rating-variance modeling (ablation)NGSAM · TwitterRMSE: 1.6011 -> 1.5011Helped
Add group-embedding loss L3 (ablation)NGSAM · Yelp 2013RMSE: 0.7368 -> 0.7163Helped
Add group-embedding loss L3 (ablation)NGSAM · Yelp 2014RMSE: 0.7177 -> 0.7031Helped
Add group-embedding loss L3 (ablation)NGSAM · TwitterRMSE: 1.5917 -> 1.5011Helped
Use more than 10 user groups (ablation)NGSAM on Yelp 2013 · Yelp 2013RMSENo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy