Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good

By Xuewei Wang, Weiyan Shi, Richard Kim, Yoojung Oh, Sijia Yang, Jingwen Zhang, Zhou Yu. 2019

375 citations recorded by the source corpus.

Developing intelligent persuasive conversational agents to change people’s opinions and actions for social good is the frontier in advancing the ethical development of automated dialogue systems. To do so, the first step is to understand the intricate organization of strategic disclosures and appeals employed in human persuasion conversations. We designed an online persuasion task where one participant was asked to persuade the other to donate to a specific charity. We collected a large dataset with 1,017 dialogues and annotated emerging persuasion strategies from a subset. Based on the annotation, we built a baseline classifier with context information and sentence-level features to predict the 10 persuasion strategies used in the corpus. Furthermore, to develop an understanding of personalized persuasion processes, we analyzed the relationships between individuals’ demographic and psychological backgrounds including personality, morality, value systems, and their willingness for donation. Then, we analyzed which types of persuasion strategies led to a greater amount of donation depending on the individuals’ personal backgrounds. This work lays the ground for developing a personalized persuasive dialogue system.

Subfields: Artificial Intelligence, Literature and Literary Theory, Sociology and Political Science, Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Literature and Literary Theory

In Sociology and Political Science

In Natural Language Processing

In Reinforcement Learning

Citations in the corpus

Experience Grounds Language (2020, background): “…et al., 2012), a myriad of tasks on visual question answering (Antol et al., 2015; Das et al., 2018), natural language and visual reasoning (Suhr et al., 2019b), visual commonsense (Zellers et al., 2019a), and multilingual captioning and translation via video (Wang et al., 2019b) have emerged.”
Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs (2022, background): “In fact, promising research has shown that using an interactive learning or multi-agent communication paradigm can enable some Theory of Mind capabilities of models (Hawkins et al., 2019; Lazaridou et al., 2020; Zhu et al., 2021; Wang et al., 2022).”
Challenges in Building Intelligent Open-domain Dialog Systems (2019, background): “PERSUASION-FOR-GOOD [147]: This corpus contains persuasion conversations for charity donation where each speaker’s psychological profile attributes and sociodemographic backgrounds such as age and income were also collected.”
How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs (2024, positive): “Our taxonomy, detailed in Table 1, classifies 40 per-suasion techniques into 15 broad strategies based on extensive social science research across psychology (Cialdini and Goldstein, 2004), communication (Dillard and Knobloch, 2011), sociology (Goff-man, 1974), marketing (Gass and Seiter, 2022), and”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “Wang et al. (2019a) proposed an incremental learning framework to train their end-to-end taskoriented system.”
MOSS: End-to-End Dialog System Framework with Modular Supervision (2019, background): “Towards tackling tasks with more dialog acts, Lewis et al. (2017); He et al. (2018); Wang et al. (2019) collected negotiation and persuasion dialogs by asking the two Turkers negotiate or persuade each other to reach an agreement.”
Advances and Challenges in Conversational Recommender Systems: A Survey (2021, background): “Leading diverse topics or explore special abilities [119, 263, 164, 102, 215]”
The rise and potential of large language model based agents: a survey (2025, positive): “Furthermore, LLM-based agents possess persuasive abilities [397], dynamically inﬂuencing human viewpoints in various interactive scenarios [398].”
SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents (2023, methodology): “On the other hand, existing interactive evaluation falls short of studying diverse goal-driven behaviors (Zhang et al., 2018b; Park et al., 2023) or focuses on specific tasks (Wang et al., 2019; Padmakumar et al., 2022; FAIR et al., 2022).”
Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models (2019, methodology): “As ARDM has already learned good language priors through pre-training, which makes it applicable on PersuasionForGood.”
Can Large Language Models Transform Computational Social Science? (2023, methodology): “We evaluate our persuasion prediction task on the Persuasion for Good Corpus (Wang et al., 2019), which contains 1,017 conversations where the persuader tries to convince the persuadee to donate to a target charity.”
CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems (2021, positive): “Several other related efforts have explored problems between task-oriented and open-domain scenarios, such as persuasion for a charity (Wang et al., 2019), anti-scam (Li et al., 2020), collecting cards in a maze (Potts, 2012), and searching for a mutual friend (He et al., 2017).”