Sentiment Analysis On User And Product
Metriken
IMDB (Acc)
Yelp 2013 (Acc)
Yelp 2014 (Acc)
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||||
|---|---|---|---|---|
| MA-BERT | 57.3 | 70.3 | 71.4 | - |
| HUAPA | 55.0 | 68.3 | 68.6 | Improving Review Representations with User Attention and Product Attention for Sentiment Classification |
| BiLSTM+CHIM | 56.4 | 67.8 | 69.2 | Rethinking Attribute Representation and Injection for Sentiment Classification |
| BiLSTM + linear-basis-cust | - | 67.1 | - | Categorical Metadata Representation for Customized Text Classification |
| CMA | 54.0 | 66.4 | 67.6 | Cascading Multiway Attentions for Document-level Sentiment Classification |
| DUPMN | 53.9 | 66.2 | 67.6 | Dual Memory Network Model for Biased Product Review Classification |
| HCSC | 54.2 | 65.7 | - | Cold-Start Aware User and Product Attention for Sentiment Classification |
| NSC | 53.3 | 65.0 | 66.7 | - |
| UPDMN | 46.5 | 63.9 | 61.3 | Capturing User and Product Information for Document Level Sentiment Analysis with Deep Memory Network |
| UPNN | 43.5 | 59.6 | 60.8 | - |
0 of 10 row(s) selected.