In recent years, personality has been regarded as a valuable personal factor being incorporated into numerous tasks such as sentiment analysis and product recommendation. This has led to widespread attention to text-based personality recognition task, which aims to identify an individual's personality based on given text. Considering that ChatGPT has recently exhibited remarkable abilities on various natural language processing tasks, we provide a preliminary evaluation of ChatGPT on text-based personality recognition task for generating effective personality data. Concretely, we employ a variety of prompting strategies to explore ChatGPT's ability in recognizing personality from given text, especially the level-oriented prompting strategy we designed for guiding ChatGPT in analyzing given text at a specified level. We compare the performance of ChatGPT on two representative real-world datasets with traditional neural network, fine-tuned RoBERTa, and corresponding state-of-the-art task-specific model. The experimental results show that ChatGPT with zero-shot chain-of-thought prompting exhibits impressive personality recognition ability. Triggered by zero-shot chain-of-thought prompting, ChatGPT outperforms fine-tuned RoBERTa on the two datasets and is capable to provide natural language explanations through text-based logical reasoning. Furthermore, relative to zero-shot chain-of-thought prompting, zero-shot level-oriented chain-of-thought prompting enhances the personality prediction ability of ChatGPT and reduces the performance gap between ChatGPT and corresponding state-of-the-art task-specific model. Besides, we also conduct experiments to observe the fairness of ChatGPT when identifying personality and discover that ChatGPT shows unfairness to some sensitive demographic attributes such as gender and age.

翻译：近年来，人格被视为一种有价值的个人因素被纳入诸如情感分析和产品推荐等众多任务中。这使得基于文本的人格识别任务受到广泛关注，该任务旨在根据给定文本识别个体人格。鉴于ChatGPT近期在多种自然语言处理任务中展现出卓越能力，我们对ChatGPT在基于文本的人格识别任务上的表现进行了初步评估，以生成有效的人格数据。具体地，我们采用多种提示策略探索ChatGPT从给定文本中识别人格的能力，特别是我们设计的面向层次的提示策略，用于引导ChatGPT在指定层次上分析给定文本。我们在两个代表性真实数据集上，将ChatGPT的表现与传统神经网络、微调后的RoBERTa以及对应的最优任务专用模型进行了比较。实验结果表明，采用零样本思维链提示的ChatGPT展现出令人印象深刻的人格识别能力。在零样本思维链提示下，ChatGPT在两个数据集上均优于微调后的RoBERTa，并能够通过基于文本的逻辑推理提供自然语言解释。此外，与零样本思维链提示相比，零样本面向层次思维链提示增强了ChatGPT的人格预测能力，并缩小了ChatGPT与对应最优任务专用模型之间的性能差距。同时，我们还通过实验观察了ChatGPT识别人格时的公平性，发现ChatGPT对某些敏感人口属性（如性别和年龄）表现出不公平性。