Human-like Interface Research Articles

Exploring ChatGPT as a writing assessment tool

ABSTRACT This research paper employs an exploratory framework to evaluate the potential of ChatGPT as an Automated Writing Evaluation (AWE) tool in teaching English as a Foreign Language (EFL) in Thailand. The main objective is to investigate how well ChatGPT can assess students’ writing using prompts and pre-defined rubrics compared to human raters. Moreover, the study examines its strengths and weaknesses as an assessment tool by analysing the teachers’ reflections during the assessment process. Quantitative analyses revealed significant relationships between trial accounts in comparison with the human ratings. Qualitative analysis unearths patterns in the feedback, shedding light on ChatGPT’s strengths and its limitations as an AWE tool. ChatGPT displays substantial promise as an AWE tool, offering distinct features such as human-like interface, consistency, efficiency, and scalability. Nonetheless, educators must be cognisant of its limitations. This study recognises that the strategic use of ChatGPT could enhance the evaluation process among teachers and foster the development of EFL students’ written communication skills.

Toward Human-Like Representation Learning for Cognitive Architectures

Human-like learning includes an ability to learn concepts from a stream of embodiment sensor data. Echoing previous thoughts such as those from Barsalou that cognition and perception share a common representation system, we suggest an addendum to the common model of cognition. This addendum poses a simultaneous semantic memory and perception learning that bypasses working memory, and that uses parallel processing to learn concepts apart from deliberate reasoning. The goal is to provide a general outline for how to extend a class of cognitive architectures to implement a more human-like interface between cognition and embodiment of an agent, where a critical aspect of that interface is that it is dynamic because of learning.

Evaluation of ChatGPT's Real-Life Implementation in Undergraduate Dental Education: Mixed Methods Study.

The recent artificial intelligence tool ChatGPT seems to offer a range of benefits in academic education while also raising concerns. Relevant literature encompasses issues of plagiarism and academic dishonesty, as well as pedagogy and educational affordances; yet, no real-life implementation of ChatGPT in the educational process has been reported to our knowledge so far. This mixed methods study aimed to evaluate the implementation of ChatGPT in the educational process, both quantitatively and qualitatively. In March 2023, a total of 77 second-year dental students of the European University Cyprus were divided into 2 groups and asked to compose a learning assignment on "Radiation Biology and Radiation Protection in the Dental Office," working collaboratively in small subgroups, as part of the educational semester program of the Dentomaxillofacial Radiology module. Careful planning ensured a seamless integration of ChatGPT, addressing potential challenges. One group searched the internet for scientific resources to perform the task and the other group used ChatGPT for this purpose. Both groups developed a PowerPoint (Microsoft Corp) presentation based on their research and presented it in class. The ChatGPT group students additionally registered all interactions with the language model during the prompting process and evaluated the final outcome; they also answered an open-ended evaluation questionnaire, including questions on their learning experience. Finally, all students undertook a knowledge examination on the topic, and the grades between the 2 groups were compared statistically, whereas the free-text comments of the questionnaires were thematically analyzed. Out of the 77 students, 39 were assigned to the ChatGPT group and 38 to the literature research group. Seventy students undertook the multiple choice question knowledge examination, and examination grades ranged from 5 to 10 on the 0-10 grading scale. The Mann-Whitney U test showed that students of the ChatGPT group performed significantly better (P=.045) than students of the literature research group. The evaluation questionnaires revealed the benefits (human-like interface, immediate response, and wide knowledge base), the limitations (need for rephrasing the prompts to get a relevant answer, general content, false citations, and incapability to provide images or videos), and the prospects (in education, clinical practice, continuing education, and research) of ChatGPT. Students using ChatGPT for their learning assignments performed significantly better in the knowledge examination than their fellow students who used the literature research methodology. Students adapted quickly to the technological environment of the language model, recognized its opportunities and limitations, and used it creatively and efficiently. Implications for practice: the study underscores the adaptability of students to technological innovations including ChatGPT and its potential to enhance educational outcomes. Educators should consider integrating ChatGPT into curriculum design; awareness programs are warranted to educate both students and educators about the limitations of ChatGPT, encouraging critical engagement and responsible use.

Speech production under uncertainty: how do job applicants experience and communicate with an AI interviewer?

Abstract Theories and research in human–machine communication (HMC) suggest that machines, when replacing humans as communication partners, change the processes and outcomes of communication. With artificial intelligence (AI) increasingly used to interview and evaluate job applicants, employers should consider the effects of AI on applicants’ psychology and performance during AI-based interviews. This study examined job applicants’ experience and speech fluency when evaluated by AI. In a three-condition between-subjects experiment (N = 134), college students had an online mock job interview under the impression that their performance would be evaluated by a human recruiter, an AI system, or an AI system with a humanlike interface. Participants reported higher uncertainty and lower social presence and had a higher articulation rate in the AI-evaluation condition than in the human-evaluation condition. Through lowering social presence, AI evaluation increased speech rate and reduced silent pauses. Findings inform theories of HMC and practices of automated recruitment and professional training.

JAICOB: A Data Science Chatbot

The application of natural language to improve students’ interaction with information systems is demonstrated to be beneficial. In particular, advances in cognitive computing enable a new way of interaction that accelerates insight from existing information sources, thereby contributing to the process of learning. This work aims at researching the application of cognitive computing in blended learning environments. We propose a modular cognitive agent architecture for pedagogical question answering, featuring social dialogue (small talk), improved for a specific knowledge domain. This system has been implemented as a personal agent to assist students in learning Data Science and Machine Learning techniques. Its implementation includes the training of machine learning models and natural language understanding algorithms in a human-like interface. The effectiveness of the system has been validated through an experiment.

COMPUTERS AS TOOLS OR AS SOCIAL ACTORS? — THE USERS' PERSPECTIVE ON ANTHROPOMORPHIC AGENTS

Surprising findings showing that many basic rules of social interaction among humans also apply to the interaction of humans with computers26 have encouraged interface researchers to proclaim a new paradigm in human computer interface design: the social interface. Reeves and Nass' findings have especially given a new impetus to research on anthropomorphic agents, suggesting that furnishing an agent with a human-like interface could be an effective way to enhance agent usability. Little research exists however, to verify this claim. This study seeks to illuminate user responses to an anthropomorphic agent if it is used on a daily basis. It examines the influence of traditional usability variables such as control, understanding, trust, and distraction on the acceptance of an anthropomorphic interface. Kaasinen8 as well as Wexelblat and Maes36 emphasize that the acceptance of agents (whether or not they have an anthropomorphic interface) strongly depends on these traditional usability variables. As subject for this study, a commonly used anthropomorphic agent, the Microsoft Office Assistant, was selected. Using a questionnaire that was distributed through email and the World Wide Web as well as on paper, 105 users of the Microsoft Office Suite were asked about their use and acceptance of the Office Assistant. It turned out that the Office Assistant feature was rejected by the majority of the users. As a feature to troubleshoot problems, it was perceived as inefficient. Also, from a "social" perspective, it was rated as not particularly engaging or motivating. Multiple regression analysis revealed that variables influencing the use and the acceptance of the Office Assistant were distraction and trust. Only those users who felt distracted by the assistant and who did not trust in its capability to solve their problems rejected the Office Assistant. It is concluded that to ensure agent usability, its design should emphasize assistance with the user's task over social mimicry. If design efforts to furnish the agent with social traits interfere with the user's principal goal, it is likely that the agent will be rejected.

Visual Recognition of Static/Dynamic Gesture: Gesture-Driven Editing System

This paper presents the visual recognition of static gesture (SG) or dynamic gesture (DG). Gesture is one of the most natural interface tools for human–computer interaction (HCI) as well as for communication between human beings. In order to implement a human-like interface, gestures could be recognized using only visual information such as the visual mechanism of human beings; SGs and DGs can be processed concurrently as well. This paper aims at recognizing hand gestures obtained from the visual images on a 2D image plane, without any external devices. Gestures are spotted by a task-specific state transition based on natural human articulation. SGs are recognized using image moments of hand posture, while DGs are recognized by analyzing their moving trajectories on the hidden Markov models (HMMs). We have applied our gesture recognition approach to gesture-driven editing systems operating in real time.

Cooperating with life-like interface agents

As computer interfaces can display more life-like qualities such as speech output and personable characters or agents, it becomes important to understand and assess users’ interaction behavior within a social interaction framework rather than only a narrower machine interaction one. We studied how the appearance of a life-like interface agent influenced people’s interaction with it, using a social interaction framework of making and keeping promises to cooperate. Participants played a social dilemma game with a human confederate via realtime video conferencing or with one of three interface agents: a person-like interface agent, a dog-like interface agent, or a cartoon dog interface agent. Technology improvements from a previous version of the human-like interface led to increased cooperation with it; participants made and kept promises to cooperate with the person-like interface agent as much as with the confederate. Dog owners also made and kept promises to dog-like interface agents. General evaluations of likability and appealingness of the interface agent did not lead people to cooperate with it. Our findings demonstrate the importance of placing user interface studies within a social interaction framework as interfaces become more social.

The electronic mirror: Human-computer interaction and change in self-appraisals

As computers become increasingly powerful and complex, software designers are employing anthropomorphism to enhance the usability of computer interfaces (i.e., “user-centered” design). The potential for implementing a social mode of interface behavior, however, can only be realized through understanding the role anthropomorphism plays in modifying the behavior and perceptions of users. The present study compares human-like versus machine-like interactional styles of computer interfaces, testing hypotheses that evaluative feedback conveyed through a human-like interface will have greater impact on individuals' self-appraisals. College students received experimentally manipulated positive or negative computerized feedback in response to their performance on a purported “psychic ability” task. In general, computer feedback had considerable impact upon reflected appraisals (participants' perceptions of the computer's evaluations of their performance and ability) as well as upon their self-appraisals of performance and ability. Reflected appraisals were more influenced by computer feedback than were self-appraisals. Human-like and machine-like interface styles did not have significantly different effects.