An official website of the United States government
We present a novel methodology for crafting effective public messages by combining large language models (LLMs) and conjoint analysis. Our approach personalizes messages for diverse personas – context-specific archetypes representing distinct attitudes and behaviors – while reducing the costs and time associated with traditional surveys. We tested this method in public health contexts (e.g., COVID-19 mandates) and civic engagement initiatives (e.g., voting). A total of 153 distinct messages were generated, each composed of components with varying levels, and evaluated across five personas tailored to each context. Conjoint analysis identified the most effective message components for each persona, validated through a study with 2,040 human participants. This research highlights LLMs’ potential to enhance public communication, providing a scalable, cost-effective alternative to surveys, and offers new directions for HCI, particularly for the design of adaptive, user-centered, persona-driven interfaces and systems.
more »
« less
A Data Analytics Approach to Persona Development for The Future Mobile Office
The concept of using automated vehicles as mobile workspaces is now emerging. Consequently, the in- vehicle environment of automated vehicles must be redesigned to support user interactions in performing work-related tasks. During the design phase, interaction designers often use personas to understand target user groups. Personas are representations of prototypical users and are constructed from user surveys and interview data. Although data-driven, large samples of user data are typically assessed qualitatively and may result in personas that are not representative of target user groups. To create representative personas, this paper demonstrates a data analytics approach to persona development for future mobile workspaces using data from the occupational information network (O*NET). O*NET consists of data on 968 occupations, each defined by 277 features. The data were reduced using dimensionality reduction and 7 personas were identified using cluster analysis. Finally, the important features of each persona were identified using logistic regression.
more »
« less
- Award ID(s):
- 1839484
- PAR ID:
- 10317865
- Date Published:
- Journal Name:
- Proceedings of the Human Factors and Ergonomics Society Annual Meeting
- Volume:
- 64
- Issue:
- 1
- ISSN:
- 2169-5067
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Throughout the mechanical design process, designers, the majority of whom are men, often fail to consider the needs of women, resulting in consequences ranging from inconvenience to increased risk of serious injury or death. Although these biases are well studied in other fields of research, the mechanical design field lacks formal investigation into this phenomenon. In this study, engineering students (n = 301) took a survey in which they read a Persona describing a student makerspace user and a Walkthrough describing the user’s interaction with the makerspace while completing a project. During the Walkthrough, the user encountered various obstacles or Pain Points. Participants were asked to recall and evaluate the Pain Points that the user encountered and then evaluated their perceptions of the makerspace and user. The independent variables under investigation were the gender of the user Persona (woman, gender-neutral, or man), the Walkthrough room case (crafting or woodworking makerspace), and the modality of the Persona and Walkthrough (text- or audio-based). Results showed that participants from the Text-based modality were better able to recall Pain Points compared to participants from the Audio-based modality. Pain Points were assessed as more severe when they impacted women users, potentially stemming from protective paternalism. In addition to finding that the gender of a user impacted the way a task environment was perceived, results confirmed the presence of androcentrism, or “default man” assumptions, in the way designers view end users of unknown gender. Promisingly, providing user Persona information in an audio modality significantly reduced this bias compared to text-based modalities, indicating that providing richer detail in user personas has the capability to reduce gender bias in designers.more » « less
-
Conversational agents designed to interact through natural language are often imbued with human-like personalities. At times, the agent might also have a distinct persona with traits such as gender, age, or a backstory. Designing such personality or persona for conversational agents has become a common design practice. In this work, we review the emerging literature on designing agent persona or personality, and reflect on these approaches, along with the personas that are created for common conversational agents. We discuss open questions with regards to three aspects: meeting user needs, the ethics of deception, and reinforcing social stereotypes through conversational agents. We hope this work can provoke researchers and practitioners to critically reflect on their approach for designing personality or persona of conversational agents.more » « less
-
Personalized response selection systems are generally grounded on persona. However, a correlation exists between persona and empathy, which these systems do not explore well. Also, when a contradictory or off-topic response is selected, faithfulness to the conversation context plunges. This paper attempts to address these issues by proposing a suite of fusion strategies that capture the interaction between persona, emotion, and entailment information of the utterances. Ablation studies on the Persona-Chat dataset show that incorporating emotion and entailment improves the accuracy of response selection. We combine our fusion strategies and concept-flow encoding to train a BERT-based model which outperforms the previous methods by margins larger than 2.3% on original personas and 1.9% on revised personas in terms of hits@1 (top-1 accuracy), achieving a new state-of-the-art performance on the Persona-Chat datasetmore » « less
-
Purpose Personas are lifelike characters that are driven by potential or real users’ personal goals and experiences when interacting with a product. Personas support user-centered design by focusing on real users’ needs. However, the use of personas in educational research and design requires certain adjustments from its original use in human-computer interface design. This paper aims to propose a process of creating personas from phenomenographic studies, which helps us create data-grounded personas effectively. Design/methodology/approach Personas have features that can help address design problems in educational contexts. The authors compare the use of personas with other common methodologies in education research, including phenomenology and phenomenography. Then, this study presents a six-step process of building personas using phenomenographic study as follows: articulate a design problem, collect user data, assemble phenomenographic categories, build personas, check personas and solve the design problem using personas. The authors illustrate this process with two examples, including the redesign of a professional development website and an undergraduate research program design. Findings The authors find that personas are valuable tools for educational design websites and programs. Phenomenography can productively help educational designers and researchers build sets of personas following the process the authors propose. Originality/value The use and method of personas in educational contexts are scarce and vague. Using the example contexts, the authors provide educational designers and researchers a clear method of creating personas that are relatable and applicable for their design problems.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1177/1071181320641240
