Even though generative artificial intelligence (GenAI) is increasingly integrated into user-facing technologies like social media, its impact on content marketing remains unverified. Early evidence suggests that language models (LLMs) can generate content that rivals human-created content (HCC) in terms of appeal. However, the question of adapting such content for various social media platforms remains unanswered. This study examines the effectiveness of an LLM, GPT-4, in customizing cross-platform content for Facebook, Instagram, and X. A total of 892 participants evaluated 30 pairs of AI-created content (ACC) and HCC. The findings reveal that ACC was preferred by users, delivered stronger calls to action, and elicited more user engagement than HCC, especially on Facebook, with a less pronounced effect for shorter posts on X and Instagram. We further generated six data-driven user personas of the 892 participants, illustrating the differences between those who preferred ACC or HCC on the three platforms. The results indicate that GPT-4 can adapt content to platform-specific requirements and maintain high perceived quality, making LLMs applicable for cross-platform content creation for user engagement. Findings contribute to understanding user engagement with AI-generated content across platforms. We also discuss the role of LLMs in content creation, including their ethical implications.

We analyzed 83 persona prompts from 27 research articles that used large language models (LLMs) to generate user personas. Findings show that the prompts predominantly generate single personas. Several prompts express a desire for short or concise persona descriptions, which deviates from the tradition of creating rich, informative, and rounded persona profiles. Text is the most common format for generated persona attributes, followed by numbers. Text and numbers are often generated together, and demographic attributes are included in nearly all generated personas. Researchers use up to 12 prompts in a single study, though most research uses a small number of prompts. Comparison and testing multiple LLMs is rare. More than half of the prompts require the persona output in structured format, such as JSON, and 74% of the prompts insert data or dynamical variables. We discuss the implications of increased use of computational personas for user representation.

This study investigates the hardware-related usability challenges that arise when using an entry-level Electroencephalography (EEG) device, specifically the Emotiv EPOC+, in user studies involving female participants. We focused on how head size and hair characteristics impact EEG signal quality and conducted a time-controlled training and usability session with five participants. We assessed hair density, texture, and length through self-reports and visual verification, and measured head circumference directly. Our results show that participants with thicker hair and larger head sizes had greater difficulty achieving proper electrode-scalp contact, which increased impedance and reduced signal quality. Additionally, participants with straight hair experienced slippage that compromised headset stability. As an exploratory pilot case study, this work identifies critical inclusivity gaps in current EEG headset design and offers actionable insights for HCI researchers aiming to improve the usability of EEG technologies for diverse female participants.

While many user researchers remain skeptical of synthetic users generated by large language models (LLMs), their adoption is growing in industry. This conceptual article investigates the root causes driving synthetic user adoption, maps potential use cases, and identifies key risks. Our inquiry reveals that while synthetic users emerge from legitimate pressures in user research, they present fundamental methodological and epistemological challenges. Their normative biases and inability to generate novel insights make them particularly problematic for user research activities like usability testing and user interviews. However, the emergence of synthetic users underlines challenges in user research, including resource constraints, privacy concerns, and difficulties in demonstrating the return on investment. Rather than simply dismissing synthetic users, we argue that understanding them as a symptom of these underlying challenges can inform efforts to strengthen the HCI research methodology.

This research investigates the practicality of automated data collection methods as an alternative to human observation in physical space wayfinding studies. Traditional approaches for capturing foot traffic and navigational behavior are often labor-intensive and resource-demanding. To address these challenges, we conducted a study assessing the feasibility of using QR codes to collect observational data. Thirteen participants navigated a national public library while their movements were tracked through strategically placed QR codes and concurrently by human observers. Analysis revealed that QR codes offer comparable precision in recording navigational data while potentially reducing the need for human labor. However, issues such as missed scans, environmental constraints, confusion with unrelated codes, and the absence of contextual insights suggest that while QR codes may enhance observational research in public settings, they should be integrated with traditional methods rather than serving as a complete replacement.

Although personas have been applied for two decades, not much is known about why a designer chooses a specific persona for a given design task. This question matters because if designers prefer one persona over another, then the needs and attributes of that persona would be favored in the design process, resulting in possible “blind spots” and bias in regards to other personas. To explore reasons and behaviors associated with the choice of a persona, we conduct an on-site user study with 37 participants in a workplace setting focused on a social media content creation task. Our findings show that factors affecting the choice of persona include age similarity between the persona and the designer, persona’s looks, how many users the persona represents, time spent browsing the persona information, and whether the persona is (a)typical relative to other personas. Under different persona sets, these factors were correlated with the probability of a persona being chosen for a design task, and also supported by a qualitative analysis of the think-aloud records where the participants explained their persona choice. The findings provide implications for developing interaction techniques that support users’ varying information needs and persona selection strategies, including recommenders that would increase the match between the designers’ information needs and the available personas.

Human-computer interaction (HCI) and natural language processing (NLP) can engage in mutually beneficial collaboration. This article summarizes previous literature to identify grand challenges for the application of NLP in quantitative user personas (QUPs), which exemplifies such collaboration. Grand challenges provide a collaborative starting point for researchers working at the intersection of NLP and QUPs, towards improved user experiences. NLP research could also benefit from focusing on generating user personas by introducing new solutions to specific NLP tasks, such as classification and generation. We also discuss the novel opportunities introduced by Generative AI to address the grand challenges, offering illustrative examples.

Our research goal is to summarize the body of persona knowledge by identifying knowledge claims. This can aid HCI researchers to (a) navigate persona knowledge to form an understanding of what is known about personas quickly, (b) identify central research gaps of what is not known (or said) about personas, and (c) identify claims that are not substantiated with strong empirical evidence and warrant future work. To this end, we use computational and manual techniques to extract 130 knowledge claims based on 9139 sentences from 346 persona articles and analyze whether the existing literature supports these claims. The results, clustered into four groups (“Definition”, “Creation”, “Evaluation”, and “Use”), indicate that claims regarding persona definition are characterized by a higher degree of consensus. In contrast, persona creation and use contain a high proportion of unverified claims. There are few claims concerning evaluation. Empirical research should address unverified claims and develop the ontological understanding on persona evaluation.

User studies have found persona application challenging. We argue that a potential reason for the challenges is the organization's readiness to apply personas. This research reports the on-going effort of developing the Persona Readiness Scale, a survey instrument for organizations’ readiness for personas. The scale involves twenty-two items from seven dimensions: Need Readiness, Culture Readiness, Knowledge Readiness, Resource Readiness, Data and Systems Readiness, Capability Readiness, and Goal Readiness. Organizations can apply the current scale to evaluate their persona readiness but using the dimensions for statistical analyses requires further empirical validation.

In this work, we build on research on data-driven personas to present what might be “wrong with them”. From wrong assumptions by the client and wrong applications of methods to imbalanced, messy, or superficial data; a lack of communication regarding how these personas are created; and issues with usability, there are a plethora of issues that plague data-driven personas. We conclude by contemplating whether data-driven personas are even worthwhile and, if they are, then what are some of the immediate remedies required from the human-computer interaction community to make data-driven personas a viable tool for user understanding.

Observing user interactions with interactive persona systems offers important insights for the design and application of such systems. Using an interactive persona system, user behavior and interaction with personas can be tracked with high precision, addressing the scarcity of behavioral persona user studies. In this research, we introduce and evaluate an implementation of persona analytics based on mouse tracking, which offers researchers new possibilities for conducting persona user studies, especially during times when in-person user studies are challenging to carry out.