Recommendations for designing conversational companion robots with older adults through foundation models

To alleviate loneliness among older adults, companion robots can provide users with the opportunity to reconnect with friends and family, thereby, mitigating the risks of over-reliance on interaction with technology. Foundation models capable of utilizing tools for social media, phones, and various devices (see Wang et al. (2024) for a survey) that leverage edge computing can enable this functionality (e.g., Dong L. et al., 2023; Shen et al., 2023). Additionally, robots can facilitate new online connections for users by harnessing their social media networks with the assistance of other deep learning architectures (e.g., Ding et al. (2017); Chen et al. (2020). Third, although this study discussed the impact of chatbot communication style on consumer satisfaction and behavior in the situation of chatbot service failure, we have only focused on the interaction initiated by consumers (i.e., consumer inquiries). Therefore, we can continue to explore the psychological and behavioral impact of the interaction initiated by chatbots on consumers in the future. For instance, “uninvited” interactions may threaten consumers’ perceived autonomy (Pizzi et al., 2021), and social-oriented communication styles may be seen as insincere, leading to feelings of disgust.

Even if a chip works the way it’s designed, though, that’s no guarantee that the chosen design is the best possible option for a specific application. Microchips are the foundation of modern technology, and historically, the process of designing them has been left up to a few highly skilled engineers. Creators who produce quality online content have a lot to gain by being cited by a chatbot.

However, after consumers experience a failed shopping experience, the degree of consumers’ expectancy violations will determine the effectiveness of the chatbot style. It is effective for companies to adopt chatbots with social-oriented communication style. Service failures touch off higher expectancy violations by consumers, where companies can focus on social orientation to enhance the warmth of interactions when deploying chatbot conversations. The adoption of chatbots with a social-oriented communication style by companies could be an effective strategy. Therefore, the expectancy violations caused by failure and matching communication style can generate a favorable evaluation and more patronage intention. However, adopting chatbots with social-oriented communication style can effectively alleviate consumers’ stressful encounters but cannot completely help consumers solve problems.

As pointed out by recent research, there is an enormous potential that chatbots hold for addressing mental health-related issues (Følstad and Brandtzaeg, 2017; Brandtzaeg and Følstad, 2018). Following ELIZA, a litany of chatbots and other applications were developed to provide self-guided mental health support for symptom relief (Tantam, 2006). A ChatGPT App meta−analysis of 23 randomized controlled trials found that some of these self-guided applications were as effective as standard face-to-face care (Cuijpers et al., 2009). Likewise, embodied conversational agents (ECAs) can be used in cognitive-based therapy (CBT) for addressing anxiety, mood and substance use disorders (Provoost et al., 2017).

It is crucial to construct the content that is appropriate for learners’ levels and personal characteristics (Lin and Mubarok, 2021). Careful consideration should be given to various factors such as family structure, social norms, and financial circumstances when designing activities to ensure meaningful engagement for students (Vazhayil et al., 2019). A systematic approach is needed to provide learners with a meaningful and accessible learning experience (Woolf et al., 2013; El Shazly, 2021; Yang, 2022). As the results of utilizing AI chatbots in classroom settings have shown positive effects in cognitive and affective domains, the need for systematic principles in designing lessons using AI chatbots has been emphasized.

Chatbot UX Example: GOCC Smart Chatbot

Khroma transcends the role of a basic color tool by understanding your color preferences and delivering customized palettes. It makes finding the right color combination easier and ensures consistency in your designs. Whether you’re looking for color inspiration or aiming for uniformity across your projects, Khroma is an excellent choice.

Optimizing the chatbot user interface (UI) is crucial for enhancing user experience. Visual elements significantly guide users through interactions and maintain their interest. Utilizing visuals such as images, buttons, and other UI elements can significantly increase user engagement and information retention. In conclusion, designing intuitive user flows requires a thorough understanding of user behavior and a commitment to continuous improvement. By focusing on user needs and providing clear pathways for task completion, you can create a chatbot that offers a seamless and satisfying user experience. Identifying potential user sticking points during the design phase is crucial for continuous improvement.

To best understand ArtPrompt and how it works, it is probably simplest to check out the two examples provided by the research team behind the tool. In Figure 1 above, you can see that ArtPrompt easily sidesteps the protections of contemporary LLMs. The tool replaces the ‘safety word’ with an ASCII art representation of the word to form a new prompt.

Dimensions of mind perception

Chatbot is driven by AI as a conversational agent, allowing users to search text-based information and conversation (Lester et al., 2004). With the increasing complexity of AI interaction technology, distinguishing between human-computer and human-to-human interaction becomes more challenging. Similar conclusions could be drawn from human interactions with chatbots (Reeves and Nass, 1996). When the chatbot is socially competent, it might be considered an automated social presence (Van Doorn et al., 2017), where individuals may feel that they are engaging with someone else during human-computer contact. Therefore, human-computer interactions reflect interpersonal interactions to some extent. Researchers argue that the principles of interpersonal interaction theory can be extended to human-computer interactions (Westerman et al., 2020; Gambino et al., 2020).

Participatory design (co-design) has been proposed as a solution to design more inclusive and suitable companion robots for older adults, and to promote mutual learning between participants and researchers (Lee et al., 2017; Kuoppamäki et al., 2023). This approach takes participants’ self-perceived thoughts and opinions into consideration and highlights factors that influence their attitudes towards robots in developing robot concepts, applications, and interaction modalities. Companion robots are socially assistive robots that are designed to respond to the social, emotional, and cognitive needs of older adults and enhance their quality of life, activity, and participation.

The chatbots’ accuracy should be ensured with confidence and protected-data safety maintained, and they should be tested by patient groups and diverse communities. In general, people can’t help robots — and other bots — behave better unless they understand why the AI acts as it does. “It’s understanding what’s happening inside the AI models,” Ramanauskas explains.

Recognizing concerns about data privacy and reuse, Curiously also employs best practices for data security and privacy, even in its early stages. Teachers have full control over what information they share, if any, and uploaded materials aren’t accessed for any function chatbot design other than enhancing a specific chatbot, according to Zheng. The author(s) declared that they were an editorial board member of Frontiers, at the time of submission. S2 Do you think the robot could help you reduce or strengthen the experience of loneliness?

OpenAI is hiding some details of this process to maintain its competitive advantage. That said, you still get charged for these in the form of “reasoning tokens.” This further emphasizes why you need to be careful about using OpenAI o1, so you don’t get charged a ton of tokens for asking where the capital of Nevada is. „To do this, we need a paradigm shift in how AI is created – one that emphasizes co-production with diverse communities throughout the entire lifecycle, from design to deployment.” „The development of AI tools must go beyond just ensuring effectiveness and safety standards,” he said in a statement. The inclusive approach, according to Dr Tomasz Nadarzynski, who led the study at the University of Westminster, is crucial for mitigating biases, fostering trust and maximizing outcomes for marginalized populations. These newer developments have brought fresh creative, ethical and legal questions, from concerns over AI porn to copyrighted works being used without permission, to “fake” songs made by digital doppelgangers of real, living artists such as Drake and the Weeknd.

That’s why it’s ever more important to make sure it doesn’t exhibit bad behavior. Today, more mature code-generation technology, coupled with advanced image models, has dramatically shortened the journey from a mere idea to a fully operational application. This improvement in efficiency opens a new era of possibilities, inviting generative AI into the heart of the creative process. In this article, we’d like to explore the fast-moving AI interface-design landscape and venture into some exciting possibilities that these technologies will unlock. Chatterbot combines a spoken language data database with an artificial intelligence system to generate a response.

We suggest that increases in warmth and competence perception, as factors in the chatbot’s communication style, will benefit consumers’ experiences of service failure. Individuals generally use warmth and competence to attribute their minds to inanimate objects (Pitardi et al., 2021); i.e., the perception of warmth reflects social-emotional, and competence perception gives expression to functional (Wirtz et al., 2018). The chatbot is regarded as lacking a mind and does not generate ideas regarding social judgments (Pitardi et al., 2021).

Artificial intelligence is used to construct a computer program known as „a chatbot” that simulates human chats with users. It employs a technique known as NLP to comprehend the user’s inquiries and offer pertinent information. Chatbots have various functions in customer service, information retrieval, and personal support.

You can foun additiona information about ai customer service and artificial intelligence and NLP. Most prominently, large language models (LLMs) enabled the development of companion robots with social skills due to their ability to process and produce language in an open-domain manner, without restriction on topics or concepts. Recent work incorporated LLMs for open-domain dialogue with robots in therapy (Lee et al., 2023), service (Cherakara et al., 2023), and elderly care (Irfan et al., 2023) domains, revealing their strengths and weaknesses in multi-modal contexts across diverse application areas. These studies underscore the versatility of LLMs in facilitating human-robot interaction (HRI). Firstly, using chatbots’ social-oriented communication style is more conducive to improving consumers’ interaction satisfaction, trust, and patronage intention.

Furthermore, there is a wide range of English proficiency levels among students in the classroom. However, assignments are uniformly provided, making it too easy for proficient students to practice the target language in the textbook, resulting in a lack of motivation to participate in the learning process. On the other hand, struggling students find it too difficult to even speak the target language and therefore refrain from verbal participation. Therefore, teachers need to explore the use of various Edu-tech tools in line with the current trends to address these issues and provide personalized lessons tailored to students’ levels, while offering effective feedback.

• Randomized control trials found that Paro reduced stress and anxiety (Petersen et al., 2017) as well as increased social interaction (Wada and Shibata, 2007) in the elderly.
• Fourth, detailed guidance on the usage and task activities of AI chatbots is necessary.
• Utilizing analytic platforms to track the chatbot’s performance allows for informed adjustments to improve future interactions.

Microsoft Designer is Microsoft’s intelligent design and image generation platform. It empowers users to create and edit various visuals, from posters and presentations to social media posts, using generative AI prompts. Yes, you can use AI to design a product by utilizing the technology to help generate ideas, analyze user data, create prototypes, test products, and customize the user experience.

Furthermore, social exclusion not only hurts when it comes from loved ones or in-group members, it is also distressing and painful when the person is excluded by out-group members (Smith and Williams, 2004). The Novartis researchers reported that it can extract data from unstructured reports, as well as annotate images or lab results, add missing data points (by predicting values in results) and identify subgroups among a population that responds uniquely to a treatment. Zou’s group at Stanford has developed PLIP, an AI-powered search engine that lets users find relevant text or images within large medical documents.

To alleviate loneliness, ElliQ proactively provides daily reminders and check-ins for health measures, gives news, weather and sports updates, makes small talk, encourages connection with family and friends, plays music, and offers games and trivia for older adults. However, it is unclear how this learning occurs due to proprietary software, which is updated every 3–4 weeks (Broadbent et al., 2024). The robot was deployed to older adults across 15 programs from various healthcare organizations in the US and Canada since its release in 2022. A study with 173 users who used the robot over 30 days showed that 80% agreed to feel less lonely with the robot. However, despite the effectiveness of proactivity in addressing loneliness (Ring et al., 2013), some users were surprised or annoyed by the proactive features (Broadbent et al., 2024). Other studies supported the negative perceptions of proactive features of the robot, such as being perceived to be talking a lot, threatening their independence, lacking compassion, and being rude, invasive, intrusive, or patronizing (Deutsch et al., 2019; Coghlan et al., 2021).

Beyond cool technology and efficiency gains for developers and designers, there also are some exciting advances in new software interfaces leveraging dynamic UI generation. Under the influence of these two trends, we’re seeing a spate of tools emerge that revamp the design-to-implementation workflow. With each prompt resulting in a handful of mockups, the focus shifts from filling a blank canvas to inspiring creativity. For a designer, the process of fleshing out design becomes less about pixel manipulation and more about ideating.

Stakeholders stressed the importance of identifying public health disparities that conversational AI can help mitigate. They said that should happen from the outset, as part of initial needs assessments – and performed before tools are created. The researchers interviewed 33 key stakeholders from diverse backgrounds, including 10 community members, doctors, developers and mental health nurses with expertise in reproductive health, sexual health, AI and robotics, and clinical safety, they said. But these approaches didn’t work as well as simply hard-coding each task into the bot. It showed that a virtual world like Minecraft can help researchers discover what works and what doesn’t when it comes to building safer bots.

Anthropic launched an Android app for its Claude AI chatbot.

To take it a step further, for certain apps where the API and data model are fixed, the user interface can largely be inferred instead of designed. This is most common for internal applications, where most operations are CRUD into an existing database, and where the primary goals of the interface are to control and validate data types, as well as to control access. Existing no-code apps such as Airtable or Smartsheet are turning data tables into CRUD apps that have implemented this with a pure rule-based approach, but AI advances are certainly taking application development to the next level. A Python chatbot is an artificial intelligence-based program that mimics human speech. Python is an effective and simple programming language for building chatbots and frameworks like ChatterBot. You’ll need the ability to interpret natural language and some fundamental programming knowledge to learn how to create chatbots.

This way, businesses can achieve their AI strategic goals securely and sustainably. As mentioned above, Microsoft Designer AI also allows you to customize and edit existing images, based on your needs. You can use the “Restyle Image” tool to choose from various styles for your photos and visuals. The new prompt templates, building on the existing templates offered by Microsoft, are increasingly impressive. These templates are already populated with ideas, styles, and descriptions you can customize to suit your needs. This is perfect if you’re new to using generative AI for design purposes and need help ensuring you get the right images with prompts.

These applications can offer help when face-to-face treatment is unavailable (Miner et al., 2016). Additionally, they may assist in overcoming the stigma around mental illness. People expect therapeutic conversational agents to be good listeners, keep secrets and honor confidentiality (Kim et al., 2018).

But there’s still plenty of work ahead to ensure that the virtual bots and physical robots we already have behave well. That’s especially true in a world where some people might try to use AI to cause harm. Plus, like that Minecraft bot, machines may also act out on accident when they don’t fully understand what not to do. Another example is Coframe’s implementation of dynamic-image and text-variant serving. The smallest atomic elements in a web app are texts and images, and LLMs and image models are great at creating variations for both.

It takes your 2D design and, with the power of machine learning, transforms it into a 3D model. Alpaca interprets the depth and perspective of your design, rendering ChatGPT a three-dimensional model that provides a more realistic view of your project. AutoDraw, created by Google, showcases how accessible AI design tools can be.

However, such considerations are not afforded to other virtual objects that do not act or appear human (Brave and Nass, 2007; Epley et al., 2007; see also Nguyen and Masthoff, 2009; Khashe et al., 2017). For example, people are more likely to cooperate with a conversational agent that has a human-like face rather than, for instance, an animal face (Friedman, 1997; Parise et al., 1999). Third, the present study found that the interaction style impacts human-computer interaction design.