Pat Pataranutaporn

• Doctor of Philosophy
• PhD Candidate in Human-AI Interaction at Massachusetts Institute of Technology

AI chatbots, especially those with voice capabilities, have become increasingly human-like, with more users seeking emotional support and companionship from them. Concerns are rising about how such interactions might impact users' loneliness and socialization with real people. We conducted a four-week randomized, controlled, IRB-approved experiment...

Pro-environmental behavior (PEB) is vital to combat climate change, yet turning awareness into intention and action remains elusive. We explore large language models (LLMs) as tools to promote PEB, comparing their impact across 3,200 participants: real humans (n=1,200), simulated humans based on actual participant data (n=1,200), and fully syntheti...

Marine ecosystems face unprecedented threats from climate change and plastic pollution, yet traditional environmental education often struggles to translate awareness into sustained behavioral change. This paper presents OceanChat, an interactive system leveraging large language models to create conversational AI agents represented as animated mari...

We investigate whether artificial intelligence can address the peer review crisis in economics by analyzing 27,090 evaluations of 9,030 unique submissions using a large language model (LLM). The experiment systematically varies author characteristics (e.g., affiliation, reputation, gender) and publication quality (e.g., top-tier, mid-tier, low-tier...

Surnames often convey implicit markers of social status, wealth, and lineage, shaping perceptions in ways that can perpetuate systemic biases. This study investigates whether and how surnames influence AI-driven decision-making, focusing on their effects across key areas such as hiring recommendations, leadership appointments, and loan approvals. D...

This paper presents our vision of TeleAbsence, extending the concept of telepresence to the past and the afterlife to address the vast emotional and temporal distance caused by the memory of loved ones who drifted apart and faded away. Instead of explicit and literal representations of loved ones, TeleAbsence describes poetic encounters with digita...

As artificial intelligence becomes increasingly sophisticated, companion chatbots have been proposed as a potential solution to the growing epidemic of loneliness. However, the impact of these AI companions on users' psychological well-being and social behaviors remains poorly understood. This study presents a large-scale survey (n = 404) of regula...

AI is increasingly used to enhance images and videos, both intentionally and unintentionally. As AI editing tools become more integrated into smartphones, users can modify or animate photos into realistic videos. This study examines the impact of AI-altered visuals on false memories--recollections of events that didn't occur or deviate from reality...

This paper introduces Text2Tradition, a system designed to bridge the epistemological gap between modern language processing and traditional dance knowledge by translating user-generated prompts into Thai classical dance sequences. Our approach focuses on six traditional choreographic elements from No. 60 in Mae Bot Yai, a revered Thai dance repert...

This study investigates psychological factors influencing belief in AI predictions about personal behavior, comparing it to belief in astrology and personality-based predictions. Through an experiment with 238 participants, we examined how cognitive style, paranormal beliefs, AI attitudes, personality traits, and other factors affect perceived vali...

This paper presents a comprehensive analysis of how AI-generated medical responses are perceived and evaluated by non-experts. A total of 300 participants gave evaluations for medical responses that were either written by a medical doctor on an online healthcare platform, or generated by a large language model and labeled by physicians as having hi...

This study examines the impact of AI on human false memories -- recollections of events that did not occur or deviate from actual occurrences. It explores false memory induction through suggestive questioning in Human-AI interactions, simulating crime witness interviews. Four conditions were tested: control, survey-based, pre-scripted chatbot, and...

Advanced Artificial Intelligence (AI) systems, specifically large language models (LLMs), have the capability to generate not just misinformation, but also deceptive explanations that can justify and propagate false information and erode trust in the truth. We examined the impact of deceptive AI generated explanations on individuals' beliefs in a p...

This research introduces an approach for translating traditional dance knowledge into interactive computational models extending beyond static dance performance recordings. Specifically, this paper presents the concept of "Human-AI co-dancing," which involves integrating human dancers with virtual dance partners powered by models derived from dance...

We introduce "Future You," an interactive, brief, single-session, digital chat intervention designed to improve future self-continuity--the degree of connection an individual feels with a temporally distant future self--a characteristic that is positively related to mental health and wellbeing. Our system allows users to chat with a relatable yet A...

As conversational agents powered by large language models become more human-like, users are starting to view them as companions rather than mere assistants. Our study explores how changes to a person’s mental model of an AI system affects their interaction with the system. Participants interacted with the same conversational AI, but were influenced...

A pilot program for synthetic biology education via a scalable distributed network model of distance-based laboratory learning can be accessible globally across disciplines and backgrounds.

The ability to discern between true and false information is essential to making sound decisions. However, with the recent increase in AI-based disinformation campaigns, it has become critical to understand the influence of deceptive systems on human information processing. In experiment (N=128), we investigated how susceptible people are to decept...

Indoor formaldehyde pollution released from household products is one of the major causes of several health diseases. Ornamental plants have been paid more attention recently to improve air quality and increase natural decorative appeal. Therefore, we aimed to use ornamental plants as a plant-based biosensor or phytosensor to monitor/detect indoor...

We are now entering the new space age! In 2021, for the first time in history that there is civilian crew in space, demonstrating the next frontier of human space exploration that will not be restricted to highly trained astronauts but will be open to a more general public. However, keeping a human healthy, happy and productive in space is one of t...

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent COVID-19 pandemic fueled a surge in the use of video conferencing tools. Since videos take up considerable bandw...

Advancements in machine learning have recently enabled the hyper-realistic synthesis of prose, images, audio and video data, in what is referred to as artificial intelligence (AI)-generated media. These techniques offer novel opportunities for creating interactions with digital portrayals of individuals that can inspire and intrigue us. AI-generate...

Sensor technology and advanced sensing systems are today experiencing a radical transformation which is affecting the way to conceive daily life. Sensors and sensing systems may improve the quality of life by providing more and more efficient care, safety, and new services for better living.

Video represents the majority of internet traffic today leading to a continuous technological arms race between generating higher quality content, transmitting larger file sizes and supporting network infrastructure. Adding to this is the recent COVID-19 pandemic fueled surge in the use of video conferencing tools. Since videos take up substantial...

Microbe-HCI is a community whose works implicate micro-organisms in HCI. This special interest group is a venue for the first gathering of the community, offering an opportunity for networking and structured discussions. It encourages participation from both active and new researchers to microbe-HCI, with the objective of acquiring an overview of p...

Space travel and becoming an interplanetary species have always been part of human's greatest imagination. Research in space exploration helps us advance our knowledge in fundamental sciences, and challenges us to design new technology and create new industries for space. However, keeping a human healthy, happy and productive in space is one of the...

Microbe-HCI is a community whose works implicate micro-organisms in HCI. This special interest group is a venue for the first gathering of the community, offering an opportunity for networking and structured discussions. It encourages participation from both active and new researchers to microbe-HCI, with the objective of acquiring an overview of p...

The home is a place of shelter, a place for family, and for separation from other parts of life, such as work. Global challenges, the most pressing of which are currently the COVID-19 pandemic and climate change have forced extra roles into many homes and will continue to do so in the future. Biodesign integrates living organisms into designed solu...

We presented the concept of “Embodied Spiritual Machine”, a type of technology that embody the known religious/spiritual figure by learning the figure’s remaining artifacts. We implemented Buddha Bot as an example of the embodied spiritual machine using NLP and semantic computing. Through online participatory study, we presented our preliminary fin...

We presented “Mind-Controlled 3D Printer” that translates brain signals from the user into 3D printed food. This system integrated an EEG recording device that measures neural activities in real-time with a machine learning algorithm that classify emotional valence and arousal levels, which determine the shape and size of the food fabricated by the...

We explore the vision of closed-loop bio-digital interfaces for human augmentation, where the bio-digital system allows for both sensing and writing biological information to the body. Current-generation wearable devices sense an individual's physiological data such as heart rate, respiration, electrodermal activity, and EEG, but lack in sensing th...

2020 Owner/Author. Having good mentors and role models is important for personal growth. However, they are not always available at the time of need. Some of our personal heroes have passed away leaving only their wisdom through writings and other artifacts. We present Wearable Wisdom, an intelligent, audio-based system for mediating wisdom and advi...

2020 Owner/Author. Having good mentors and role models is important for personal growth. However, they are not always available at the time of need. Some of our personal heroes have passed away leaving only their wisdom through writings and other artifacts. We present Wearable Wisdom, an intelligent, audio-based system for mediating wisdom and advi...

This paper presents a design and performance analysis of the passive microgravity sensor. The passive microgravity sensor is specially designed for non-electric supplied payload, which was launched in Mission 9 of New Shepard, Blue origin. Due to the weightlessness during microgravity, the general mass-spring systems with appropriate mass and sprin...

Wearables are being widely researched for monitoring individual's health and wellbeing. Current generation wearable devices sense an individual's physiological data such as heart rate, respiration, electrodermal activity, and EEG, but lack in sensing their biological counterparts, which drive the majority of individual's physiological signals. On t...

Sense is a responsive garment that visualizes the global phenomenon of coral bleaching. Sense examines the current scientific shift in which technology converges with biology and embody the beauty, power and fragility of nature. This project explores aesthetic territory at the intersection of traditional textile techniques and wearable technologies...

Catching up to the frontier of space exploration requires tremendous resources, knowledges, and infrastructures. As a consequence, the space education is perceived as the process for accelerating the space technology development. This paper focuses on the lessons, challenges, and outcomes from the first national CanSat competition in Thailand by lo...

The ubiquitous and pervasive nature of computing fosters intimate relationships between humans and computers as the digital objects being entangled with “non” digital objects: biological, tangible, and cultural. We present the framework of the human-magical interaction, which defines the emerging interfaces as forms of “Magic” emphasizing the seaml...

Biological HCI (Bio-HCI) framework is a design framework that investigate the relationship between human, computer and biological systems by redefining biological materials as design elements. Bio-HCI focuses on three major components: biological materials, intermediate platforms, and interactions with the user. This framework is created through co...

Based on the context of higher life expectancy and lower pregnancy rate, ageing society is unavoidable. Technological response is necessary. Hormone Couture exhibition presents two wearable technologies that aesthetically respond to women's reproductive hormone and body temperature changes. The designs address how technology creates a biopolitical...

In nature, the formation of iron sulfide solids is mainly attributed to reductions of sulfate and ferric minerals by microorganisms such as Desulfovibrio vulgaris. In order to evaluate the impacts on microbial activity and optimize iron sulfide production for potential application in uranium remediation, we tested two types of electron donors (lact...