# Persuasive Dialogue Understanding: the Baselines and Negative Results

arXiv: https://arxiv.org/abs/2011.09954 · HTML: https://mlsanity.com/paper/2011.09954/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 3 of 3)

- [Must Read: A Comprehensive Survey of Computational Persuasion](https://mlsanity.com/paper/2505.07775/) (2025)
- [Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue](https://mlsanity.com/paper/2203.07657/) (2022)
- [Do You Know My Emotion? Emotion-Aware Strategy Recognition towards a Persuasive Dialogue System](https://mlsanity.com/paper/2206.12101/) (2022)

## Abstract (arXiv)

Persuasion aims at forming one's opinion and action via a series of persuasive messages containing persuader's strategies. Due to its potential application in persuasive dialogue systems, the task of persuasive strategy recognition has gained much attention lately. Previous methods on user intent recognition in dialogue systems adopt recurrent neural network (RNN) or convolutional neural network (CNN) to model context in conversational history, neglecting the tactic history and intra-speaker relation. In this paper, we demonstrate the limitations of a Transformer-based approach coupled with Conditional Random Field (CRF) for the task of persuasive strategy recognition. In this model, we leverage inter- and intra-speaker contextual semantic features, as well as label dependencies to improve the recognition. Despite extensive hyper-parameter optimizations, this architecture fails to outperform the baseline methods. We observe two negative results. Firstly, CRF cannot capture persuasive label dependencies, possibly as strategies in persuasive dialogues do not follow any strict grammar or rules as the cases in Named Entity Recognition (NER) or part-of-speech (POS) tagging. Secondly, the Transformer encoder trained from scratch is less capable of capturing sequential information in persuasive dialogues than Long Short-Term Memory (LSTM). We attribute this to the reason that the vanilla Transformer encoder does not efficiently consider relative position information of sequence elements.