Product Tag: web based manipulation

web based chatbot with AI integration for testing psychological connection with ai agents

Web-Based AI Chatbot Experimental Paradigm

This web-based experimental paradigm was developed to investigate how different AI chatbot response styles and conversational strategies influence users’ psychological and social responses during human–AI interaction. The platform connects to OpenAI models through an API key and allows researchers to define custom system prompts that dynamically shape the chatbot’s behavior throughout the interaction.

Researchers can configure different experimental conditions by modifying the chatbot’s instructions, making it possible to manipulate dimensions such as relational versus non-relational communication, empathy, warmth, conversational responsiveness, self-disclosure, interaction style, and conversation structure or depth. Because these manipulations are implemented through customizable prompts, the paradigm can be adapted to a wide range of experimental questions while maintaining a standardized web-based interaction environment.

The paradigm was used to manipulate chatbot conversational behavior in the research reported by Telari, Gabbiadini, and Riva (2026). Across two experimental studies, the authors manipulated the chatbot’s response style (relational vs. non-relational) and, in the second study, the depth of conversation topics (high vs. low) to examine how different forms of AI-mediated interaction influence perceived responsiveness, empathy, self-disclosure, interpersonal closeness, and intentions for future use. The experimental prompts were specifically designed to produce either warm, empathic, and socially responsive interactions or more detached and task-oriented conversational styles.

Reference

Telari, A., Gabbiadini, A., & Riva, P. (2026). Can humans feel connected to AI? Perceived responsiveness drives social connection with AI chatbots. Journal of Social and Personal Relationships, 43(9), 2579–2600. https://doi.org/10.1177/02654075261438164

web based manipulation for working objectification elicited by Artificial intelligence social psychology

STEMI – AI Recruitment Paradigm

STEMI is a web-based experimental paradigm developed to investigate the psychological consequences of being evaluated by artificial intelligence in a workplace context. The paradigm simulates a realistic online recruitment process and allows researchers to manipulate whether candidates are evaluated by an AI-based recruiter or a human recruiter, providing an ecologically relevant framework for studying work self-objectification, perceived self-efficacy, agency, and beliefs in free will.

The paradigm is built around the website of a fictitious company, STEMI, where participants are asked to imagine applying for an open job position. After entering the experimental environment, participants explore the company website and encounter a recruitment banner advertising available positions. They are then invited to apply for the position and proceed to an online job interview through the website’s integrated chat system.

Depending on the experimental condition, participants are informed that their interview will be conducted either by an AI recruiter or by a human HR recruiter. In both conditions, the interview follows the same predefined structure and questions, allowing the identity of the evaluating agent to be manipulated while keeping the content of the interaction as comparable as possible. During the original implementation, both the AI system and the human operator were instructed to redirect participants to the recruitment task whenever the conversation deviated from the interview.

The interaction reproduces several key features of contemporary algorithmic recruitment. In the AI condition, participants interact with a natural-language-processing system designed to conduct candidate screening and extract relevant information from their responses. The interview therefore places participants in a situation in which their personal characteristics and experiences are transformed into information that can be analysed by an algorithm. This makes the paradigm particularly suitable for investigating datafication and work self-objectification—that is, the possibility that individuals come to perceive themselves less as autonomous human agents and more as data, instruments, or resources evaluated according to externally defined criteria.

In its original implementation, the simulated interview lasted approximately 40 minutes. At the end of the interaction, both the AI and human recruiter informed participants that the selection process had concluded and asked them to wait for the result. Participants subsequently received unsuccessful selection feedback. Psychological measures were then administered to assess outcomes including self-efficacy, self-objectification, beliefs in free will, realistic threat, and human identity threat.
The STEMI paradigm was used in Study 2 of Gabbiadini et al. (2025) as a more ecologically valid extension of earlier scenario-based experiments. The study showed that interacting with an AI recruiter, compared with a human recruiter, was associated with lower perceived self-efficacy and greater work self-objectification. The broader research suggests that AI-mediated evaluation may reduce individuals’ perceived agency by placing them in an externally controlled and highly data-driven evaluative process.

Reference

Gabbiadini, A., Durante, F., Baldissarri, C., Manfredi, A., Sterlicchio, A., & Romano, S. (2025). Artificial intelligence in the workplace: Effects on self-efficacy, self-objectification and beliefs in free will. Journal of Community & Applied Social Psychology, 35, e70107. https://doi.org/10.1002/casp.70107

cyberball italian version social exclusion

Cyberball – Italian enhanced version

Cyberball is a widely used experimental paradigm developed to study the psychological consequences of social exclusion and ostracism. It takes the form of a simple virtual ball-tossing game in which participants believe they are interacting online with other players, although the behavior of the other players is actually controlled by the experimental program.

In the original paradigm, participants are typically told that the task concerns mental visualization and are asked to imagine the interaction while taking part in a virtual ball-tossing game. They play together with two or more apparent participants and can choose to whom they want to throw the ball whenever they receive it. The apparent co-players are in fact computer-controlled, allowing the experimenter to systematically manipulate the participant’s level of social inclusion.

The interaction generally involves three main phases. First, participants receive instructions introducing the virtual ball-tossing task and are led to perceive the other players as interaction partners. During an initial inclusion phase, the ball is distributed relatively evenly among the players, allowing the participant to experience normal social participation. In the ostracism or exclusion condition, the other players subsequently stop—or substantially reduce—throwing the ball to the participant and instead exchange it primarily with one another. In comparison, participants assigned to an inclusion condition continue receiving the ball throughout the game. This simple manipulation reliably produces an experience of being ignored or excluded despite the minimal and artificial nature of the interaction.

Cyberball has become one of the most established paradigms for investigating responses to social exclusion, including changes in belonging, perceived control, self-esteem, meaningful existence, affect, and subsequent social behavior. The original research showed that even exclusion occurring in a brief computer-mediated interaction can negatively affect participants’ sense of belonging and control.

Custom Italian Version

The version available here is a customized Italian implementation of the Cyberball paradigm, designed for use in experimental research. It preserves the core logic of the original social inclusion/exclusion manipulation while providing a modernized graphical interface and an improved visual presentation.

The paradigm is configurable in Italian, allowing researchers to adapt the experimental setup and interaction parameters to the requirements of their study. This version is intended to provide a more contemporary and flexible implementation of the classic Cyberball task while maintaining its central experimental mechanism for manipulating perceived social inclusion and exclusion.

Original Reference

Williams, K. D., Cheung, C. K. T., & Choi, W. (2000). Cyberostracism: Effects of being ignored over the Internet. Journal of Personality and Social Psychology, 79(5), 748–762. https://doi.org/10.1037/0022-3514.79.5.748

web based application for testing romantic rejection online dating app social psychology

Cupidoo – Experimental Online Dating Paradigm

Cupidoo is an experimental online dating paradigm designed to investigate the psychological consequences of romantic rejection and social feedback in digital environments. The platform reproduces the core features of an online dating service while allowing researchers to maintain experimental control over participants’ interactions and the feedback they receive from potential partners.

During the experience, participants create a personal dating profile and are led to believe that the platform uses their profile information and interests to identify compatible romantic partners. They are then presented with a set of potential partners and asked to select those they find most appealing. The system can subsequently manipulate the outcome of these interactions, for example by providing romantic rejection from the selected partners or an appropriate control condition. This makes Cupidoo particularly suitable for experimentally studying social exclusion, emotional responses to rejection, interpersonal aggression, attitudes toward potential partners, and other psychosocial processes associated with online dating.

The paradigm was originally developed and used in the study “Lonely Hearts and Angry Minds: Online Dating Rejection Increases Male (but Not Female) Hostility”, where it was employed to experimentally investigate how rejection from desired online dating partners influences emotional and hostile responses. In that study, participants selected three potential partners; in the rejection condition, all three declined the participant’s matching request, whereas the control condition prevented partner feedback through an ostensible technical failure.

Reference
Andrighetto, L., Riva, P., & Gabbiadini, A. (2019). Lonely hearts and angry minds: Online dating rejection increases male (but not female) hostility. Aggressive Behavior, 45(5), 571–581. https://doi.org/10.1002/ab.21852