When two people pay attention to each other and are interested in what the other has to say or write, they almost instantly adapt their writing/speaking style to match the other. For a successful interaction with a user, chatbots and dialogue systems should be able to do the same. We propose a framework consisting of five psycholinguistic textual characteristics for better human-computer interaction. We describe the annotation processes used for collecting the data, and benchmark five binary classification tasks, experimenting with different training sizes and model architectures. The best architectures noticeably outperform several baselines and achieve macro-averaged F$_1$-scores between 72\% and 96\% depending on the language and the task. The proposed framework proved to be fairly easy to model for various languages even with small amount of manually annotated data if right architectures are used.
Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features
RWTH-Aachen University（亚琛工业大学）；University of Amsterdam（阿姆斯特丹大学）
人格心理学、计算机科学和语言学的交叉研究最近越来越多地关注从语言使用中建模和预测人格。我们报告了从文本数据预测人格特质的两个主要改进：（1）据我们所知，最全面的基于理论的心理语言学特征集和（2）混合模型，该模型集成了预训练的Transformer语言模型BERT和双向长短期记忆（BLSTM）网络，这些网络在心理语言学特征的文本内分布（“文本轮廓”）上进行训练。我们使用BLSTM模型（有和没有注意力）进行实验，并使用两种技术来应用来自Transformer模型的预训练语言表示-“基于特征”和“微调”。我们评估了我们在两个基准数据集上构建的模型的性能，这两个基准数据集针对两个主要的人格理论模型：Big Five Essay数据集和MBTI Kaggle数据集。我们的结果令人鼓舞，因为我们的模型在相同的数据集上优于现有的工作。更具体地说，我们的模型在Essay数据集上的分类准确率提高了2.9%，在Kaggle MBTI数据集上提高了8.28%。此外，我们进行消融实验，以量化不同类别的心理语言学特征在各自的人格预测模型的影响。
Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM
Institute of Science Tokyo（东京科学大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；Fujitsu Limited（富士通株式会社）
