Persona Profiles Research Articles

How large language model-powered conversational agents influence decision making in domestic medical triage contexts

IntroductionEffective delivery of healthcare depends on timely and accurate triage decisions, directing patients to appropriate care pathways and reducing unnecessary visits. Artificial Intelligence (AI) solutions, particularly those based on Large Language Models (LLMs), may enable non-experts to make better triage decisions at home, thus easing the healthcare system's load. We investigate how LLM-powered conversational agents influence non-experts in making triage decisions, further studying different persona profiles embedded via prompting.MethodsWe designed a randomized experiment where participants first assessed patient symptom vignettes independently, then consulted one of the two agent profiles—rational or empathic—for advice, and finally revised their triage ratings. We used linear models to quantify the effect of the agent profile and confidence on the weight of advice. We examined changes in confidence and accuracy of triage decisions, along with participants' perceptions of the agents.ResultsIn a study with 49 layperson participants, we found that persona profiles can be differentiated in LLM-powered conversational agents. However, these profiles did not significantly affect the weight of advice. Notably, less confident participants were more influenced by LLM advice, leading to larger adjustments to initial decisions. AI guidance improved alignment with correct triage levels and boosted confidence in participants' decisions.DiscussionWhile LLM advice improves triage recommendations accuracy, confidence plays an important role in its adoption. Our findings raise design considerations for human-AI interfaces, highlighting two key aspects: encouraging appropriate alignment with LLMs' advice and ensuring that people are not easily swayed in situations of uncertainty.

Agent-based decision-support model for bus route redesign in networks of small cities and towns: case study of Agder, Norway

Small cities and towns often struggle to provide high-quality public transport services to daily commuters. This is reflected in the modal split, where the share of car users dominates. Such a problem requires a modern solution, where transport planners can verify the impact of potential transport network improvements on the travel behavior of the residents before the changes are actually deployed. This study aims to demonstrate the usefulness of employing an agent-based simulation tool in the decision process for redesigning an express service regional bus route connecting a network of small cities and towns. The model was initially developed as a Mobility as a Service simulation solution for suburban areas of European metropolises. The model is adapted and applied to a case study for the region of Agder, Norway, simulating the impact of nine different scenarios on the patronage of a specific bus route. The simulation model proposes to upgrade the classic agent structure to a persona profile designed specifically for the case study. The main objective of this research is to identify the scenario that maximizes patronage while minimizing total route travel time and additional costs. The results suggest that the proposed model can be successfully adapted from suburban metropolitan areas to the realities of the considered case study, and potentially other similar regions. Specifically, out of the nine proposed scenarios, the model identified four promising ones. One of the four scenarios also fits the cost constraints imposed by the transport provider. The model provides a solid approach for analyzing complex transport systems that are practically impossible to consider in detail if the analysis is done without computer support. Thus, the results can be used as a decision support system for public transport planning and operations in networks of small cities and towns.

Persona Design Methodology for Work-Commute Travel Behaviour Using Latent Class Cluster Analysis

The present study proposes a new methodology that combines quantitative and qualitative data for the generation of representative personas for commuters. The profiles can be used to better understand their travel behaviour and mode choices. The research is based on the example of the region of Agder in Norway and aims to overcome the persona development shortcomings identified by previous researchers. Data from a regional travel behaviour survey (N= 1 849) is analysed using latent class cluster analysis (LCCA), and enriched with qualitative input from 32 interviews, and information provided by an expert panel. This results in a set of 20 representative persona profiles for the case study region. The proposed methodology is easily replicable in other urban networks and has the potential to provide insight into the mobility behaviour and needs of specific groups of people in order to adapt the transport services and encourage climate-friendly behaviour.

I’m not a puppet, I’m a real boy! Gender presentations by virtual influencers and how they are received

Virtual influencers, or computer-generated virtual characters, have attracted numerous followers on social media like Instagram with their unconstrained physical bodies and persona profiles. Due to the characteristic of visibility and hyperconnectivity of social media, virtual influencers' public presentations can influence their followers and how they respond to virtual influencers and similar influencers as a collective phenomenon. Through a content analysis of 517 posts and 21,724 user comments from 17 of the most popular English-speaking human-like virtual influencers on Instagram, our study investigates how virtual influencers leverage the flexibility in presenting their affect, sexual display, virtual nature, and humanness (biological senses) and how their followers respond to these dimensions accordingly. We compared if female and male virtual influencers followed gender stereotypes in their self-presentations and if the followers responded accordingly. Our findings show that the most popular virtual influencers do not seem to leverage their flexible gender identity, but often present themselves according to gender stereotypes and receive corresponding comments based on their gender. Male virtual influencers are significantly more likely to “pass” as an actual human, while female virtual influencers are more likely to disclose their virtual nature.

The realness of fakes: Primary evidence of the effect of deepfake personas on user perceptions in a design task

Deepfakes, realistic portrayals of people that do not exist, have garnered interest in research and industry. Yet, the contributions of deepfake technology to human-computer interaction remain unclear. One possible value of deepfake technology is to create more immersive user personas. To test this premise, we use a commercial-grade service to generate three deepfake personas (DFs). We also create counterparts of the same persona in two traditional modalities: classic and narrative personas. We then investigate how persona modality affects the perceptions and task performance of the persona user. Our findings show that the DFs were perceived as less empathetic, credible, complete, clear, and immersive than other modalities. Participants also indicated less willingness to use the DFs and less sense of control, but there were no differences in task performance. We also found a strong correlation between the uncanny valley effect and other user perceptions, implying that the tested deepfake technology might lack maturity for personas, negatively affecting user experience. Designers might also be accustomed to using traditional persona profiles. Further research is needed to investigate the potential and downsides of DFs.

CPID: Insider threat detection using profiling and cyber-persona identification

In digital environments, network administrators can benefit from the advanced network traffic monitoring capabilities with respect to the type of users (persona) and their specific network activities. This can be leveraged to derive corresponding persona profiles that can be subsequently used to detect anomalies and security events. Also, upon the occurrence and detection of a security event, it is important to get full details on the underlying entities and to gain relevant insights to mitigate and prevent such occurrences in the future. In this context, this paper proposes an innovative approach leveraging machine learning techniques along with deep learning for persona-specific traffic profile generation. This capability can be deployed as part of online traffic monitoring solutions for persona identification and anomalous network behaviour detection, where no software needs to be installed on deployed workstations. Performed experiments indicate that the proposed approach is efficient, scalable, and suitable for near real-time deployment scenarios.

The Effect of First Impression on Women’s Online Social Tendency

In the realm of online dating, first impressions are pivotal, significantly influencing the trajectory of subsequent interactions and relationship development. This article examines the women’s preferences in QQ Channels towards men on online social networking platforms. The present study conducts a preliminary interview to observe the impact of different personal types (extroverted, introverted, learning-focused, and “bad boy”) on the attractiveness and interaction levels of female users. This paper draws from a diverse group of female participants, ensuring a wide range of ages and backgrounds. Four types of personal impression are created, each simulating a real dating environment, allowing participants to interact with persona profiles. The result reveals that extroverted personas are highly attractive. Introverted personas struggle to sustain interactions, often resulting in participants halting communication or failing to progress beyond initial contact. Learning personas exhibit limited engagement, with most participants tapering off after the initial interaction. Interestingly, the “bad boy” persona garners high attention. The study highlights the important role of first impressions in online communication. This provides preliminary evidence of women’s online dating behaviors on emerging social platforms.

Health and Environment Conscious Consumer Attitudes: Generation Z Segment Personas According to the LOHAS Model

As a lifestyle and consumer trend, the LOHAS (Lifestyle of Health and Sustainability) has been growing in popularity worldwide. The LOHAS is followed by a consumer group that is characterised by consumer attitudes and behaviours focusing on health and sustainability, that is increasingly concerned about global problems and challenges, and that follows trends related to sustainability, such as health and environmental consciousness. In addition, this group strives for a sense of naturalness, aims to behave ethically, and seeks to hold authentic and individualistic values. The objective of this research is to explore how young people today relate to the components of the LOHAS model, how the different characters respond, and what their perceived values are. We are also looking for answers pertaining to whether clusters may be formed based on the examined factors. In our study, we surveyed 357 Hungarian respondents, who are members of Generation Z. As a method of data analysis, descriptive statistical methods, correlation analyses, factor analysis, cluster analysis, and the persona profiles were designed using the design thinking method. Based on the factors of the LOHAS model, three separate groups may be ascertained within Generation Z: personas that fit the LOHAS, personas that could fit the LOHAS, and personas that do not fit LOHAS.

Towards mobilizing educators as environmental ambassadors: a design research approach to inspire teachers to advocate sustainable futures

PurposeThis paper aims to articulates how educators are ideal candidates to become “brand ambassadors”, triggering dormant qualities to influence behavioral change. The study aims at advocating a call for environmental futures by mobilizing pedagogues for changemaking. The research purpose was to deduce insights of real-life experiences when dealing with social influencers.Design/methodology/approachA design research approach was adopted. A sample of educators and students representing two universities of applied sciences was selected for qualitative. An experimental participatory experience was facilitated and observed.FindingsThis paper provides empirical insights. Design research findings include a persona profile, and an experimental prototype, designed to activate findings for real world impact. The outcome is for impact in the real world.Research limitations/implicationsThe research was conducted locally at a Dutch university of applied sciences, on behalf of a Norwegian commissioner. Therefore, cultural contextual conditions were factored.Practical implicationsAn applicable advice is sketched, tested and shared with non governmental organization’s, institutions or stakeholders who aspire to mobilize and activate educators, turning them into ambassadors for their cause.Social implicationsThis paper aims at contributing and taking a position within the current tensions in academia and in the educational sector, in the light of the2012 San Francisco Declaration of Research Assessment declaration and of the urgency of enabling educators to partake to climate change activism.Originality/valueBesides the engaged topic, this paper is uniquely based on a highly experiential, design thinking approach, which was co-created and facilitated in an experimental setting.

Can Unhappy Pictures Enhance the Effect of Personas? A User Experiment

There has been little research into whether a persona's picture should portray a happy or unhappy individual. We report a user experiment with 235 participants, testing the effects of happy and unhappy image styles on user perceptions, engagement, and personality traits attributed to personas using a mixed-methods analysis. Results indicate that the participant's perceptions of the persona's realism and pain point severity increase with the use of unhappy pictures. In contrast, personas with happy pictures are perceived as more extroverted, agreeable, open, conscientious, and emotionally stable. The participants’ proposed design ideas for the personas scored more lexical empathy scores for happy personas. There were also significant perception changes along with the gender and ethnic lines regarding both empathy and perceptions of pain points. Implications are the facial expression in the persona profile can affect the perceptions of those employing the personas. Therefore, persona designers should align facial expressions with the task for which the personas will be employed. Generally, unhappy images emphasize realism and pain point severity, and happy images invoke positive perceptions.

Generating Personas for Products on Social Media: A Mixed Method to Analyze Online Users

ABSTRACT The purpose of this research is to develop a methodology that combines the quantitative and the qualitative analysis to generate personas for products on social platforms. The user data on social platforms contain massive information relating to the lifestyle people have and the products people use or are interested. By analyzing the specific content generated by users on social platforms, e.g., content involving the term “tablet,” it is possible to reveal how the users consider or use the product, “tablet.” By analyzing the users’ homepages, the information relating to the users’ daily life can be found. We collected 276, 675 pieces of relevant data regarding the product, “tablet,” from 12, 965 online users on China’s widely used social media platforms. Then automatic user segments and the profiles of each group were generated and structured by natural language processing technology. The results of these quantitative analyses were then qualitatively examined by manual analyses, which provide additional insights and detailed descriptions on the automatically generated persona profiles. In this study, six personas representing distinct user types were created. The mixed method of combining the quantitative and qualitative methods makes the generation of personas faster and more insightful. The generated personas can represent real user behavior and characteristics and can provide insights into the products, which also can provide support on designing new products and optimizing existing products.

Too few, too many, just right: Creating the necessary number of segments for large online customer populations

We develop a framework to reduce the number of customer segments to the smallest quantity without losing essential information of the underlying population in the electronic marketplace. As a use case of this approach, we create personas for these segments to enhance customer understanding. We use (a) matrix factorization to identify customer behaviors and construct customer segments, (b) statistical heuristics to collapse into meaningful segments, and (c) automation to enrich by generating a persona profile for each segment. We evaluate our approach in a case study using more than 21 million online flight bookings of a major airline company resulting in a 57.5% decrease from 1194 to 507 segments, thereby reducing segment noise. Three customer mega-segments emerge: Behaviorally same – Demographically different, Behaviorally different - Demographically same, and Behaviorally and Demographically different. As one of the first efforts at the essential task of customer segmentation reduction for large customer populations, findings have implications for organizations desiring to employ segmentation and/or personas for enhanced customer understanding.

Using artificially generated pictures in customer-facing systems: an evaluation study with data-driven personas

ABSTRACT We conduct two studies to evaluate the suitability of artificially generated facial pictures for use in a customer-facing system using data-driven personas. STUDY 1 investigates the quality of a sample of 1,000 artificially generated facial pictures. Obtaining 6,812 crowd judgments, we find that 90% of the images are rated medium quality or better. STUDY 2 examines the application of artificially generated facial pictures in data-driven personas using an experimental setting where the high-quality pictures are implemented in persona profiles. Based on 496 participants using 4 persona treatments (2 × 2 research design), findings of Bayesian analysis show that using the artificial pictures in persona profiles did not decrease the scores for Authenticity, Clarity, Empathy, and Willingness to Use of the data-driven personas.

Persona profiles of Latinx living in Boston: Applications for information organizations

AbstractBased on data and initial findings of a larger phenomenological project focused on the experiences of Latinx living in the Boston area, we created two persona profiles. The persona profiles are based on preliminary results of the analysis of 13 interviews with members of the Latinx community in Boston, which identified two distinct groups among the participants. These groups were defined by socioeconomic class, as identified by two main indicators: educational attainment and English language skills. Those belonging to the lower socioeconomic class had low educational attainment and limited English language skills compared to those in the middle socioeconomic class group made up of Latinx who had high educational attainment and were fully bilingual. The persona profiles created by using the interview data have potential applications for those working in information organizations, and to help researchers and practitioners in information organizations design better services for urban Latinx communities. This approach aligns with the United Nations 2030 Agenda for Sustainable Development, which among many goals, intends to make cities and human settlements inclusive, safe, resilient and sustainable.

Translational Personas and Hospital Library Services

ABSTRACT Academic health centers, CTSA hubs, and hospital libraries experience similar funding challenges and charges to do more with less. In recent years academic health center and hospital librarians have risen to these challenges by examining their service models, and beyond that, examining their patron base and users’ needs. To meet the needs of employees, patients, and those who assist patients, hospital librarians can employ the CTS Personas, a project of the Clinical and Translational Science Awards (CTSA) Program National Center for Data to Health. The Persona profiles, which outline the motivations, goals, pain points, wants, and needs of twelve employees and two patients in translational science, provide vital information and insights that can inform everything from designing software tools and educational services, to advertising these services, to designing impactful and collaborative library spaces.

Data-Driven Personas for Enhanced User Understanding: Combining Empathy with Rationality for Better Insights to Analytics

Persona is a common human-computer interaction technique for increasing stakeholders’ understanding of audiences, customers, or users. Applied in many domains, such as e-commerce, health, marketing, software development, and system design, personas have remained relatively unchanged for several decades. However, with the increasing popularity of digital user data and data science algorithms, there are new opportunities to progressively shift personas from general representations of user segments to precise interactive tools for decision-making. In this vision, the persona profile functions as an interface to a fully functional analytics system. With this research, we conceptually investigate how data-driven personas can be leveraged as analytics tools for understanding users. We present a conceptual framework consisting of (a) persona benefits, (b) analytics benefits, and (c) decision-making outcomes. We apply this framework for an analysis of digital marketing use cases to demonstrate how data-driven personas can be leveraged in practical situations. We then present a functional overview of an actual data-driven persona system that relies on the concept of data aggregation in which the fundamental question defines the unit of analysis for decision-making. The system provides several functionalities for stakeholders within organizations to address this question.

Personas for the translational workforce.

Twelve evidence-based profiles of roles across the translational workforce and two patients were made available through clinical and translational science (CTS) Personas, a project of the Clinical and Translational Science Awards (CTSA) Program National Center for Data to Health (CD2H). The persona profiles were designed and researched to demonstrate the key responsibilities, motivators, goals, software use, pain points, and professional development needs of those working across the spectrum of translation, from basic science to clinical research to public health. The project's goal was to provide reliable documents that could be used to inform CTSA software development projects, educational resources, and communication initiatives. This paper presents the initiative to create personas for the translational workforce, including the methodology, engagement strategy, and lessons learned. Challenges faced and successes achieved by the project may serve as a roadmap for others searching for best practices in the creation of Persona profiles.

Persona Transparency: Analyzing the Impact of Explanations on Perceptions of Data-Driven Personas

ABSTRACT Computational techniques are becoming more common in persona development. However, users of personas may question the information in persona profiles because they are unsure of how it was created. This problem is especially vexing for data-driven personas because their creation is an opaque algorithmic process. In this research, we analyze the effect of increased transparency – i.e., explanations of how the information in data-driven personas was produced – on user perceptions. We find that higher transparency through these explanations increases the perceived completeness and clarity of the personas. Contrary to our hypothesis, the perceived credibility of the personas decreases with the increased transparency, possibly due to the technical complexity of the persona profiles disrupting the facade of the personas being real people. This finding suggests that explaining the algorithmic process of data-driven persona creation involves a “transparency trade-off”. We also find that the gender of the persona affects the perceptions, with transparency increasing perceived completeness and empathy of the female persona, but not for the male persona. Therefore, transparency may specifically assist in the acceptance of female personas. We provide practical implication for persona creators regarding transparency in persona profiles.

Does a Smile Matter if the Person Is Not Real?: The Effect of a Smile and Stock Photos on Persona Perceptions

ABSTRACT We analyze the effect of using smiling/non-smiling and stock photo/non-stock photo pictures in persona profiles on four key persona perceptions, including credibility, likability, similarity, and willingness to use. For this, we collect data from an experiment with 2,400 participants using a 16-item survey instrument and multiple persona profile treatments of which half have a smiling photo/stock photo and half do not. The results from structural equation modeling, supplemented by a qualitative analysis, show that a smile enhances the perceived similarity with the persona, similar personas are more liked, and that likability increases the willingness to use a persona. In contrast, the use of stock photos decreases the perceived similarity with the persona as well as persona credibility, both of which are significant predictors to a willingness to use a persona. These professionally crafted stock-photos seem to diminish the sense of identification with the persona. The above effects are consistent across the tested ages, genders, and races of the persona picture, although the effect sizes tend to be small. The results suggest that persona creators should use smiling pictures of real people to evoke positive perceptions toward the personas. In addition to presenting quantitative evidence on the predictors of willingness to use a persona, our research has implications for the design of persona profiles, showing that the picture choice influences individuals’ persona perceptions even when the other persona information is identical.

Confusion and information triggered by photos in persona profiles

Abstract We investigate whether additional photos beyond a single headshot makes a persona profile more informative without confusing the end user. We conduct an eye-tracking experiment and qualitative interviews with digital content creators after varying the persona in photos via a single headshot, a headshot and photo of the persona in different contexts, and a headshot with photos of different people with key persona attributes the gender and age. Findings show that contextual photos provide significantly more persona information to end users; however, showing photos of multiple people engenders confusion and lowers informativeness. Also, as anticipated, viewing additional photos requires more cognitive focus, which is measured by eye-tracking metrics; these metrics are correlated with levels of informativeness and confusion. Furthermore, various interpretations of the persona based on the choice of photos are biased by the end users’ experiences and preconceptions. Concerning persona design, findings indicate that persona creators need to consider the intended persona use objectives when selecting photos and when producing persona profiles. Using contextual photos can improve informativeness, but this demands more cognitive focus from end users. Thus, adding contextual photos increases the perceived informativeness of the persona profile without being obfuscating, but multiple photos of different people do evoke confusion about the targeted persona.