A set of pre-trained machine-learning models that predict (im-)politeness scores in texts.
-
Updated
Jan 2, 2025 - Jupyter Notebook
A set of pre-trained machine-learning models that predict (im-)politeness scores in texts.
One hundred years of social psychology quantitatively described
A collection of functions and scripts designed to create, manipulate, and analyze FaceGen faces and face models
Open-source toolkit for social interaction research: extract 400+ multimodal features from conversation videos, then analyze synchrony, conversational states, and impression dynamics
人机交互心理学知识库 | HRI × 社会心理:人如何感知、归因、信任、依赖非人智能体(不限载体),以及这件事对人本身意味着什么。
Construal Level International Multi-lab Replication (CLIMR) Project
Four main takeaways: (1) LLMs are subject to pressure, they comply despite expressing distress; (2) LLMs are vulnerable to gradual boundary/value violations; (3) when LLMs refuse, they may ignore the response format requirements, so the query is retried; (4) we hypothesise there is a token pattern continuation attractor that might cause obedience.
Code for "Seeing the other side: Conflict and controversy increase gaze coordination" (Paxton, Dale, & Richardson, submitted).
基于芒格逆向思维的人性动机审计引擎。专治社交虚伪、逻辑劫持与自证内耗。Stop self-justification, start incentive auditing.
Dynamic Social Impact Simulator [R Package]
A template repository for linguistic analysis of conversations from scratch using Convokit.
A highly customizable tool for generating chat record screenshots, designed for academic researchers preparing experimental stimuli and survey materials.可高度定制的聊天记录生成工具。面向科研场景,用于准备实验材料或问卷中使用的对话截图。支持样式独立调节、布局预设、JSON 导出/导入。
Moral Anger and Disgust: Recipient vs. Initiator Focus in Moral Transgressions
CosplayGIF-Project
R code for the course project replicating contagion effect by Newman (2011), supervised by Dr. Gilad Feldman. 2021.09-12
(SOC+OCC)PSYCH/R Initial website for personal and professional presence
Behavioral testbed for LLM agents on classic social-psychology paradigms (Asch, Milgram, Stanford Prison), with PsicoBench — a 7-axis social-susceptibility profile of 17 models — a preprint with frozen pre-registrations, and a Concordia-based narrative simulator.
Streetscapes at Scale: Mapping Platform APIs as a Tool to Sample Space
To associate your repository with the social-psychology topic, visit your repo's landing page and select "manage topics."