Research map / Label-efficient and robust learning / Recognition and long-tail
Sentiment Classification in Customer Service Dialogue with Topic-Aware Multi-Task Learning
Jiancheng Wang, Jingjing Wang, Changlong Sun, Shoushan Li, Xiaozhong Liu, Luo Si, Min Zhang, Guodong Zhou
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 overall topic inference auxiliary task (ablation) | TML main task · Customer service dialogue sentiment | Macro-F1: 73.4 -> 74.8 | Improved |
| add customer-role topic inference on top of overall topic (ablation) | TML · Customer service dialogue sentiment | Macro-F1: 74.8 -> 75.6 | Improved |
| add agent-role topic inference on top of overall topic (ablation) | TML · Customer service dialogue sentiment | Macro-F1: 74.8 -> 75.2 | Improved |
| add agent-role topic when customer-role and overall already present (ablation) | TML · Customer service dialogue sentiment | Macro-F1: 75.6 -> 75.9 | Improved |
| add all three topic auxiliary tasks (TML) to main task (ablation) | BERT+LSTM+attention · Customer service dialogue sentiment | Macro-F1: 73.4 -> 75.9 | Improved |
| use TML vs best baseline DialogueRNN | DialogueRNN · Customer service dialogue sentiment | Macro-F1: 73.9 -> 75.9 | Improved |
| add LDA topic features to BERT | BERT · Customer service dialogue sentiment | Macro-F1: 72.3 -> 72.5 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DialogueRNN — DialogueRNN: An Attentive RNN for Emotion Detection in Conversations (AAAI 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling (AAAI 2021 · similarity 0.87)
- An Adaptive Layer to Leverage Both Domain and Task Specific Information from Scarce Data (AAAI 2023 · similarity 0.86)
- A Speaker Turn-Aware Multi-Task Adversarial Network for Joint User Satisfaction Estimation and Sentiment Analysis (AAAI 2023 · similarity 0.83)
- CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation (AAAI 2026 · similarity 0.83)
- Topic-Aware Multi-turn Dialogue Modeling (AAAI 2021 · similarity 0.83)
- Modeling Adaptive Inter-Task Feature Interactions via Sentiment-Aware Contrastive Learning for Joint Aspect-Sentiment Prediction (AAAI 2024 · similarity 0.81)
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.
