Lune

EMNLP Findings2025

Rethinking Personality Assessment from Human-Agent Dialogues: Fewer Rounds May Be Better Than More

Baiqiao Zhang, Zhifeng Liao, Xiangxian Li, Chao Zhou, Juan Liu, Xiaojuan Ma, Yulong Bian

Abstract

Personality assessment is essential for developing user-centered systems, playing a critical role across domains including hiring, education, and personalized system design. With the integration of conversational AI systems into daily life, automatically assessing human personality through natural language interaction has gradually gained more attention. However, existing personality assessment datasets based on natural language generally lack consideration of interactivity. Therefore, we propose Personality-1260, a Chinese dataset containing 1260 interaction rounds between humans and agents with different personalities, aiming to support research on personality assessment. Based on this dataset, we designed experiments to explore the effects of different interaction rounds and agent personalities on personality assessment. Results show that fewer interaction rounds perform better in most cases, and agents with different personalities stimulate different expressions of users' personalities. These findings provide guidance for the design of interactive personality assessment systems. The dataset and code are publicly available here 1 .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on4

  1. Character-LLM: A Trainable Agent for Role-PlayingYunfan Shao, Linyang Li, Junqi Dai, Xipeng QiuEMNLP 2023 · 97 citations
  2. PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality DetectionTao Yang, Tianyuan Shi, Fanqi Wan, Xiaojun Quan et al.EMNLP Findings 2023 · 34 citations
  3. Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on DialoguesLei Sun, Jinming Zhao, Qin JinEMNLP 2024 · 6 citations
  4. Psycholinguistic Tripartite Graph Network for Personality DetectionTao Yang, Feifan Yang, Haolan Ouyang, Xiaojun QuanACL 2021

Related papers

  1. Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait AlignmentPriyanka Dey, Aayush Bothra, Yugal Khanter, Jieyu Zhao et al.EMNLP Findings 2025 · 1 citation
  2. Toward Stance-based Personas for Opinionated DialoguesThomas Scialom, Serra Sinem Tekiroglu, Jacopo Staiano, Marco GueriniEMNLP Findings 2020 · 8 citations
  3. Effects of Embodiment and Personality in LLM-Based Conversational AgentsSinan Sonlu, Bennie Bendiksen, Funda Durupinar, Ugur GüdükbayIEEE VR 2025 · 17 citations
  4. Faithful Persona-based Conversational Dataset Generation with Large Language ModelsPegah Jandaghi, XiangHai Sheng, Xinyi Bai, Jay Pujara et al.ACL Findings 2024 · 10 citations
  5. User Perceptions of Extraversion in Chatbots after Repeated UseSarah Theres Völkel, Ramona Schödel, Lale Kaya, Sven MayerCHI 2022 · 37 citations
Dusk over the sea between two cliffs drawn in fine vertical lines