“For the first time, we shared a meaningful exchange”: KAIST develops an AI app for parents and minimally verbal autistic children connect​

The Korea Advanced Institute of Science and Technology (KAIST)

WeChatBluesky
Email

 

image: 

Photo 1. (From left) Professor Hwajung Hong and Doctoral candidate Dasom Choi of the Department of Industrial Design with SoHyun Park and Young-Ho Kim of Naver Cloud AI Lab

view more 

Credit: KAIST DxD Lab

For many families of minimally verbal autistic (MVA) children, communication often feels like an uphill battle. But now, thanks to a new AI-powered app developed by researchers at KAIST in collaboration with NAVER AI Lab and Dodakim Child Development Center, parents are finally experiencing moments of genuine connection with their children.

On the 16th, the KAIST (President Kwang Hyung Lee) research team, led by Professor Hwajung Hong of the Department of Industrial Design, announced the development of ‘AAcessTalk,’ an artificial intelligence (AI)-based communication tool that enables genuine communication between children with autism and their parents.

This research was recognized for its human-centered AI approach and received international attention, earning the Best Paper Award at the ACM CHI 2025*, an international conference held in Yokohama, Japan.
*ACM CHI (ACM Conference on Human Factors in Computing Systems) 2025: One of the world's most prestigious academic conference in the field of Human-Computer Interaction (HCI). 

This year, approximately 1,200 papers were selected out of about 5,000 submissions, with the Best Paper Award given to only the top 1%. The conference, which drew over 5,000 researchers, was the largest in its history, reflecting the growing interest in ‘Human-AI Interaction.’

Called AACessTalk, the app offers personalized vocabulary cards tailored to each child’s interests and context, while guiding parents through conversations with customized prompts. This creates a space where children’s voices can finally be heard—and where parents and children can connect on a deeper level.

 

Traditional augmentative and alternative communication (AAC) tools have relied heavily on fixed card systems that often fail to capture the subtle emotions and shifting interests of children with autism. AACessTalk breaks new ground by integrating AI technology that adapts in real time to the child’s mood and environment.

 

 

< Figure. Schematics of AACessTalk system. It provides personalized vocabulary cards for children with autism and context-based conversation guides for parents to focus on practical communication. Large ‘Turn Pass Button’ is placed at the child’s side to allow the child to lead the conversation. >

 

 

Among its standout features is a large ‘Turn Pass Button’ that gives children control over when to start or end conversations—allowing them to lead with agency. Another feature, the “What about Mom/Dad?” button, encourages children to ask about their parents’ thoughts, fostering mutual engagement in dialogue, something many children had never done before.

One parent shared, “For the first time, we shared a meaningful exchange.” Such stories were common among the 11 families who participated in a two-week pilot study, where children used the app to take more initiative in conversations and parents discovered new layers of their children’s language abilities.

Parents also reported moments of surprise and joy when their children used unexpected words or took the lead in conversations, breaking free from repetitive patterns. “I was amazed when my child used a word I hadn’t heard before. It helped me understand them in a whole new way,” recalled one caregiver.

Professor Hwajung Hong, who led the research at KAIST’s Department of Industrial Design, emphasized the importance of empowering children to express their own voices. “This study shows that AI can be more than a communication aid—it can be a bridge to genuine connection and understanding within families,” she said. 

Looking ahead, the team plans to refine and expand human-centered AI technologies that honor neurodiversity, with a focus on bringing practical solutions to socially vulnerable groups and enriching user experiences.

This research is the result of KAIST Department of Industrial Design doctoral student Dasom Choi's internship at NAVER AI Lab.
* Thesis Title: AACessTalk: Fostering Communication between Minimally Verbal Autistic Children and Parents with Contextual Guidance and Card Recommendation
* DOI: 10.1145/3706598.3713792
* Main Author Information: Dasom Choi (KAIST, NAVER AI Lab, First Author), SoHyun Park (NAVER AI Lab) , Kyungah Lee (Dodakim Child Development Center), Hwajung Hong (KAIST), and Young-Ho Kim (NAVER AI Lab, Corresponding Author)

 

This research was supported by the NAVER AI Lab internship program and grants from the National Research Foundation of Korea: the Doctoral Student Research Encouragement Grant (NRF-2024S1A5B5A19043580) and the Mid-Career Researcher Support Program for the Development of a Generative AI-Based Augmentative and Alternative Communication System for Autism Spectrum Disorder (RS-2024-00458557).

Figure. Schematics of AACessTalk system. It provides personalized vocabulary cards for children with autism and context-based conversation guides for parents to focus on practical communication. Large ‘Turn Pass Button’ is placed at the child’s side to allow the child to lead the conversation.

Credit

Authors: Dasom Choi, SoHyun Park, Kyungah Lee, Hwajung Hong, Young-Ho Kim

DOI

10.1145/3706598.3713792 

Method of Research

Computational simulation/modeling

Subject of Research

People

Article Title

AACessTalk: Fostering Communication between Minimally Verbal Autistic Children and Parents with Contextual Guidance and Card Recommendation

 

Forest management can influence health benefits 

University of Surrey

Forests play a crucial role in promoting health and wellbeing, but not all forests provide the same benefits. A large-scale international study, co-led by the University of Surrey and the University of Ghent, demonstrates how specific forest characteristics – such as canopy density and tree species diversity – can affect various health outcomes.  

The research, published in Nature Sustainability, was carried out by a range of international partners within the Dr. Forest research project, investigated 164 forests across five European countries, offering valuable insights for forest management and urban planning. The study examined seven ecological characteristics of forests and their influence on different human health effects.  

Tree species diversity was found to have a limited but positive effect on human health and wellbeing. Increasing tree species diversity is therefore considered a safe and beneficial intervention for forest managers, which also provides multiple co-benefits beyond human health, such as supporting associated non-tree biodiversity. 

Forest structures – particularly, the canopy structure – were found to have the strongest health impact, both with its own benefits and drawbacks. Dense canopy reduces heat stress by providing more shade and creating a more stable microclimate, while also improving air quality by increasing leaf surface area for fine particulate matter deposition – both crucial elements in urban areas where heatwaves and airborne pollutants are more frequent.  

On the other hand, a dense canopy can also increase the risk of Lyme disease – as ticks thrive in humid climates – and lead to less light reaching the forest floor, which can hinder the growth of medicinal plants, affecting their potential health benefits. 

From a mental health standpoint, just being in a forest was found to be beneficial, reducing anxiety and stress, and increasing positive emotions. Forests that people perceived to be more biodiverse and natural were also found to be the most beneficial for mental health. 

Dr Melissa Marselle, Lecturer in Environmental Psychology at the University of Surrey, said: 

“Our study shows that forests generally provide a mental health benefit, reducing anxiety and stress, regardless of their biodiversity or structure.  As one in six people in England experience anxiety and depression each week, this research suggests that simply being in a forest can improve mental health. For the UK, this means preserving urban forests so people can easily access forests where they live, work and play for their mental wellbeing. Contact with forests could be prescribed by the NHS, as research shows that NHS nature prescriptions are effective at improving mental health.” 

[ENDS] 

 

• Dr Melissa Marselle is available for interview, please contact mediarelations@surrey.ac.uk to arrange.   

• An image of Dr Marselle is available upon request. 

---

Journal

Nature Sustainability

DOI

10.1038/s41893-025-01547-3 

 

Culture is the silent force behind slow mobile payment adoption

Cultural values that are often overlooked in technology marketing strategies play a decisive role in consumers' acceptance of mobile payment systems, according to a new study from the University of Surrey

University of Surrey

Facebook

X
Bluesky
Email

Cultural values that are often overlooked in technology marketing strategies play a decisive role in consumers' acceptance of mobile payment systems, according to a new study from the University of Surrey.  

While the increasing usage of smartphones and wallet apps (e.g. Apple Pay, Google Pay, and AliPay) has fuelled global growth in mobile payment, the adoption rate is not uniform across different countries. The paper defines mobile payments as a transfer of funds to purchase goods or services in which a mobile device executes and confirms the payment. In 2022, only 25% of users in the US adopted mobile payments, which is relatively low compared to countries in Asia such as China (72%), Thailand (65%), and India (63%)*.  

The study, published in International Marketing Review, involving a comprehensive survey of 679 respondents in the United States, investigated the relationship between individual-level cultural values and the acceptance of mobile payment technologies.  It shows that cultural value shapes consumers’ behaviour about adopting new technologies, including mobile payment. 

Traditional methods of analysing consumer behaviour often focus solely on national averages, neglecting individual cultural backgrounds that shape decision-making processes. The researchers compared two models: one assessing the direct effects of cultural orientations and another examining their moderating influences on technology acceptance. 

Dr Nima Heirati, Associate Professor of Marketing and co-author of the study at the University of Surrey, said: 

“The findings suggest that businesses must embrace a more nuanced understanding of their customers' individual-level cultural identities to create effective marketing strategies.  

“Ignoring these individual differences can lead to missed opportunities and hinder the growth of mobile payment adoption across various demographics.” 

The research identified five key individual-level cultural orientations—power distance, individualism, masculinity, uncertainty avoidance, and long-term orientation—each of which has a significant impact on how consumers perceive and adopt new technologies. For instance, those with high power distance are more likely to value ease of use and habitual engagement with mobile payments, while individuals with high uncertainty avoidance tend to prioritise trust and reliability in their payment systems. 

Dr Heirati continued: 

“Businesses must tailor their marketing strategies to resonate with specific individual-level cultural values to foster greater acceptance of mobile payments. By understanding that cultural values influence consumers’ beliefs regarding technology, businesses can develop more effective marketing messages that address the unique needs and preferences of different consumer segments.” 

 

[ENDS] 

• Dr Nima Heirati is available for interview, please contact mediarelations@surrey.ac.uk to arrange.   

• *Data gathered from Statista 

• The full paper is available in the International Marketing Review 

---

Journal

International Marketing Review

DOI

10.1108/imr-09-2023-0223/full/html 

Method of Research

Observational study

Subject of Research

People

Article Title

An investigation of culture’s influence on new technology adoption: the case of mobile payment

 

How African tourism entrepreneurs found a way to weather the storm and thrive after Covid

Tourism entrepreneurs in Sub-Saharan Africa are not only weathering the storm of environmental uncertainty but are thriving amid adversity in emerging economies, according to a new study from the University of Surrey

University of Surrey

Facebook

BlueskyMessageWhatsAppEmail

Tourism entrepreneurs in Sub-Saharan Africa are not only weathering the storm of environmental uncertainty but are thriving amid adversity in emerging economies, according to a new study from the University of Surrey.  

The study investigates the coping strategies used by micro, small, and medium-sized enterprises (MSMEs) in Ghana and Nigeria during the COVID-19 pandemic. 

The paper, published in Tourism Management, gathered data from 844 participants and conducted in-depth interviews with 23 tourism entrepreneurs to understand the lived experiences of business owners as they navigated the unprecedented challenges posed by the pandemic. 

The study found that problem-focused coping strategies—actions aimed at directly addressing challenges—significantly enhance both resilience and wellbeing among entrepreneurs. These strategies include operational adjustments (such as adjusting their daily work schedule or optimising their time management), resource management optimisations, and creative pricing tactics (such as strategies to respond to inflation or fluctuating market conditions). In contrast, emotion-focused coping strategies, which typically include emotional regulation and seeking social support, were found to be less relevant in managing the immediate challenges faced by these entrepreneurs. 

Dr Manuel Alector Ribeiro, Associate Professor in Tourism Management and lead author of the study at the University of Surrey, said: 

“Entrepreneurs in resource-scarce environments are often underestimated in their capacity to adapt and innovate under pressure.” 

“Our findings highlight their incredible resilience and the proactive strategies they employ, which are essential not only for their survival but also for the broader economic landscape of these nations.” 

Prof Albert Kimbu, Co-Director of the Centre for Sustainability and Wellbeing in the Visitor Economy and co-author of the study at the University of Surrey, said: 

“What we need to understand is that resilience is not just an individual trait but a collective effort. Policymakers and entrepreneurship educators must prioritise training programmes that equip entrepreneurs with problem-solving skills, adaptive decision-making processes, and resilience-building techniques. 

“By fostering community networks and collaborative decision-making, we can build a more robust entrepreneurial ecosystem that supports not just businesses but the livelihoods of entire communities.” 

 

[ENDS]  

Notes to editors 

• Dr Manuel Alector Ribeiro and Prof Albert Kimbu are available for interviews, please contact mediarelations@surrey.ac.uk to arrange

• The full paper is available in Tourism Management 

---

Journal

Tourism Management

Article Title

Resilience in uncertainty: The impact of coping strategies on tourism entrepreneurs’ subjective well-being in sub-Saharan Africa

 

Segregation fuels faster spread of infectious diseases, study finds

Using two major US data sets, new model reveals how deep social divides make entire communities—rich and poor alike—more vulnerable to infectious diseases

Complexity Science Hub

Facebook

XLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

The diagram shows how people’s decisions—like going to work or staying home—affect how a disease spreads, and how the spread of the disease, in turn, influences those decisions.

At the top, it shows that people with higher or lower socioeconomic status (SES) behave differently depending on how severe the outbreak is. For example, in a low-infection situation, people are more likely to go to work, while in a high-infection scenario, more people stay home to avoid getting sick.

At the bottom, we see how the disease moves through a network of people. In three snapshots, we watch how infected individuals pass the disease to others. Some people choose to quarantine (shown with dashed green circles), which means they temporarily disconnect from others and stop the spread. After a while, infected people either recover or are removed from the system. Shapes represent different SES groups, and colors show who is infected. Solid lines mean people are in contact and can spread the disease; dashed lines mean they’re not in contact.

The curved arrows in the diagram show how behavior (like deciding to quarantine) and disease spread are linked together—each influences the other in a constantly changing process.

view more 

Credit: Complexity Science Hub

[Vienna, May 20, 2025] – Structural inequalities, including wealth inequality and social segregation, not only make certain groups more vulnerable during public health crises but also accelerate the spread of infectious diseases through society, according to a team of international researchers. 

In a study published in Nature Scientific Reports, the researchers introduce a novel computational model that drew from two comprehensive US data sets—one based on economic and social network data from 404 metropolitan areas in the United States and another using daily Covid-19 infection data from Chicago—to better understand the relationship between socioeconomic factors and epidemic dynamics.

“As social segregation increases, it exacerbates not only the health inequality but also the overall prevalence of the disease. In that case, everyone will be worse off,” says first author Sina Sajjadi, from the Complexity Science Hub.

A Disease Explosion

“We found this surprising because high segregation and low interaction among groups might appear to limit transmission across socioeconomic groups, resulting in a lower infection rate,” explains Sajjadi. “In fact, it's not like that. According to our model, such high segregation will result in an explosion of the disease, which will ultimately infect others.”

“Our model shows that when people can’t effectively quarantine—especially in communities where many are closely connected—the risk of infection goes up. This close contact can lead to a rapid outbreak that spreads through the neighborhood and beyond,” adds co-author Fariba Karimi, CSH's Algorithmic Fairness team leader and professor at Graz University of Technology. 

Second Infection Wave

The computational model also predicts the appearance of a second peak in infection rates. Due to a false sense of safety, higher-income individuals, who can afford to quarantine, return to normal activities prematurely once infection rates in lower-income groups decline. This dynamic sets the stage for renewed outbreaks.

In addition, the results confirm that wealth inequality widens the infection gap. Low-income individuals, with fewer resources to self-quarantine, are more likely to be exposed to infections, leading to higher infection rates in disadvantaged communities. 

A Hypothetical “Ideal” Scenario

On the other hand, the researchers considered a hypothetical “ideal” scenario for each metropolitan area, in which all groups were homogeneously mixed. “We found that, without segregation, infection rates were lower in most metropolitan areas. A nonsegregated community would be better able to protect everyone from infectious diseases”, points out Sajjadi. 

According to the researchers, the findings underscore the urgent need for policies that address income inequality and social segregation, particularly during pandemics. “By reducing these disparities, governments can mitigate the health impacts of future crises and protect vulnerable populations,” say Sajjadi and Karimi, who worked with researchers from Turkey, the United States, and Inserm Institute in France.

 

---

About the Study

The study “Structural inequalities exacerbate infection disparities,” by Sina Sajjadi, Pourya Toranj Simin, Mehrzad Shadmangohar, Basak Taraktas, Ulya Bayram, Maria V. Ruiz-Blondet & Fariba Karimi, was published in Nature Scientific Reports and is available online (https://doi.org/10.1038/s41598-025-91008-w).

 

---

About CSH

The Complexity Science Hub (CSH) is Europe’s research center for the study of complex systems. We derive meaning from data from a range of disciplines—economics, medicine, ecology, and the social sciences—as a basis for actionable solutions for a better world. Established in 2015, we have grown to over 70 researchers, driven by the increasing demand to gain a genuine understanding of the networks that underlie society, from healthcare to supply chains. Through our complexity science approaches linking physics, mathematics, and computational modeling with data and network science, we develop the capacity to address today’s and tomorrow’s challenges.

 

---

Journal

Scientific Reports

DOI

10.1038/s41598-025-91008-w 

Method of Research

Computational simulation/modeling

Subject of Research

People

Article Title

Structural inequalities exacerbate infection disparities

 

The least confident delivery drone gets the job

Researchers from Technical University of Darmstadt and international collaborators present a study on energy-aware delivery drone operations

Technische Universitat Darmstadt

Facebook

XLinkedInWeChatBlueskyMessageWhatsAppEmail

 

video: 

AAMAS 2025: On-Demand Delivery Using Fleets of Drones with Unknown, Heterogeneous Energy Storage

view more 

Credit: NaturalRoboticsLab

At a fulfilment centre, delivery drones assign tasks among themselves using an auction-based system. Each drone considers its current battery level and evaluates whether it can complete the task. If so, it places a bid that reflects its confidence. The drone that wins the auction attempts the task and uses the outcome to refine its understanding of its true capabilities, which are influenced by unknown factors such as the long-term health of its battery. Counterintuitively, selecting the least confident bidder as the auction winner proved most effective. This approach enabled drones to learn more accurately where their performance limits lie and promotes smarter use of resources by deploying drones whose capabilities are well-matched to the task at hand.

The researchers, led by Professor Roderich Groß from the Department of Computer Science at TU Darmstadt, tested their method in a specially developed multi-agent simulator over a period of eight weeks. The results showed that the learning-based approach achieved significantly higher delivery rates and shorter delivery times compared to conventional threshold-based strategies. In an extended version, drones were even able to take on tasks that they could complete only once sufficiently recharged, enabling a forward-looking allocation of resources. ‘This work shows how online learning can help robots cope with real-world challenges, such as operating without full knowledge of their true capabilities,’ said Dr Mohamed Talamali from The University of Sheffield.

The approach can also be used to efficiently manage heterogeneous fleets in which the drones differ, for example, due to manufacturing tolerances or individual wear and tear. This paves the way for autonomously operating delivery systems with higher reliability and optimised energy usage. ‘Such autonomous delivery drones could also operate across multiple fulfilment centres, further reducing delivery times and costs,’ said Professor Groß.

The study ‘Ready, Bid, Go! On-Demand Delivery Using Fleets of Drones with Unknown, Heterogeneous Energy Storage Constraints’ will be presented on 21 May at the 24th International Conference on Autonomous Agents and Multiagent Systems in Detroit, USA, and was selected as a finalist for the Best Paper Award from more than 1,000 submissions. It received funding from the Horizon Europe project OpenSwarm.

---

DOI

10.48550/arXiv.2504.08585 

Method of Research

Computational simulation/modeling

Article Title

Ready, Bid, Go! On-Demand Delivery Using Fleets of Drones with Unknown, Heterogeneous Energy Storage Constraints