Text-based Interactions Research Articles

Creating Engaging Chatbot Experiences by Tailoring Personalities in Text-Based Interactions

Our expressive AI software is driven by creativity fused with technology. This transformative platform allows users to generate various content easily and augment their creative capacities. Through the merger of modern human-computer interaction artificial intelligence tools, people and artificial intelligent work together to come up with creative innovations. Our goal is not only about generating content but also creating avatars that have memories to foster active involvement. Expressive AI introduces digital companions with distinct personas, which enhance interactions while offering innovative ideas. Such a journey does not just change the digital content creation field. it also demonstrates how people and smart technologies can work together and create what had never been expected in terms of intelligent creativity.

Advancing Educational accessibility and experiences: A sophisticated Chatbot integration approach

The integration of chatbots into the educational sector has ushered in a new era of learning and administrative support. This review paper explores the dynamic landscape of chatbots within educational institutes, focusing on their evolution and the emergence of innovative trends. From their early days as basic information providers to their current roles as personalized learning companions, chatbots have undergone significant transformations. The study identifies key milestones in the evolution of chatbots in education, highlighting their transition from rule-based systems to intelligent learning assistants. Moreover, this review delves into the latest trends shaping the chatbot ecosystem in education. It underscores the growing emphasis on Al-powered personalization, multimodal interfaces, and integration with Learning Management Systems (LMS) to streamline administrative tasks. Chatbots are no longer confined to text-based interactions; they now support voice and video, making education more accessible and inclusive. Additionally, they are contributing to mental health support and counseling services, addressing the well-being of students. The paper will argue that chatbots have the potential to revolutionize education by providing students with personalized learning experiences, supporting students with special needs, and promoting student engagement. However, it is important to address the ethical implications of using chatbots in education, such as privacy and bias. The paper will be of interest to educators, researchers, and policymakers who are interested in learning more about the potential of chatbots to transform education. Keywords— Deep Learning, Machine learning, NLP, Voice Assistant, Linux, Artificial Intelligence, Speech Recognition, LLMs.

Saudi Female’s Arabic Requests: A Comparative Study of Face-to-Face and Text-Based Communications

This mix-method study aimed to investigate the influence of communication media on the realization of the speech act of request in Arabic. Thus, it examined the number of words and the type of modification devices in the request of 40 Saudi female postgraduate students in equal power situations across two communication channels: face-to-face and WhatsApp text-based interactions. The data is collected using a discourse completion task with four situations that varied in the degree of imposition and social distance. The collected data was analyzed quantitatively and qualitatively. Two samples t-test was used to analyze the collected data along with a modified version of Blum-Kulka and Olshtain’s (1984) coding scheme for categorizing the modification devices. The study found that participants produced more words in WhatsApp text-based communication than face-to-face communication, but no significant difference was found except in the context of (+I, +D). External modifiers were produced more than internal ones, especially grounders. Social distance influenced modifier frequency, while imposition only affected disarmers. The study implies modification devices are obligatory rather than optional in Saudi culture.

Conversational AI

Abstract: Conversational AI systems are becoming increasingly popular across many industries and are transforming the way people interact with technology. For a more authentic, human-like connection and a smooth user experience, these systems should combine text-based interactions with multimodal capabilities. The authors of this work suggest a new approach to improving conversational AI systems' usability by combining speech and visual analysis. By combining visual and auditory processing capabilities, AI systems can better understand human inquiries and instructions. Both visual data and speech can be better understood with the use of computer vision algorithms and natural language processing techniques, respectively. Conversational AI systems can provide more accurate and tailored replies by integrating many modalities to better grasp human intent and context. The development of multimodal conversational AI presents a significant difficulty in ensuring the smooth integration of voice and visual processing units. A strong architectural design and advanced algorithms are necessary for the simultaneous synchronization and comprehension of data from several modalities in real-time. The system needs to keep track of the conversation's context even when it switches between different forms of communication so it can keep providing fair and relevant responses all through the engagement. Customization is key to making multimodal conversational AI better for users. Based on user data and preferences, the system may tailor interactions to offer more relevant ideas and support. Users are more invested in the AI system over time, and they have a better experience overall because to customization. Ensuring the privacy and security of important audiovisual data is of the utmost importance while building multimodal conversational AI. Strong encryption, anonymization technologies, and compliance with data protection regulations are vital for user privacy and system confidence. Continuous improvement is key to the success of multimodal conversational AI systems. The feedback from users can help the developers improve the system and add new features. Thanks to this iterative technique, the AI system stays flexible and can adjust to changing consumer preferences. By combining voice and picture processing, conversational AI systems have a great deal of promise for improving the user experience. Through the integration of visual and auditory signals, these systems have the ability to comprehend user intent more accurately, provide customized experiences, and completely transform the way humans engage with technology.

Emojis And Miscommunication in Text-Based Interactions Among Nigerian Youths

This paper explores the dynamic role of emojis in text-based communication among Nigerian youths and the potential implications for miscommunication. Emojis have become integral to contemporary digital conversations, offering users a visual means of expressing emotions, tone, and context within the constraints of text-based interactions. In the context of Nigeria, a country with a diverse linguistic landscape and a youthful population heavily engaged in online communication, understanding the impact of emojis on interpersonal exchanges becomes particularly pertinent. This paper examines the prevalence and patterns of emoji usage among Nigerian youths across various digital platforms. It investigates the cultural nuances and interpretations associated with emojis within the Nigerian context, considering factors such as regional differences, linguistic diversity, and socio-cultural influences. Furthermore, the study examines instances where emojis may contribute to miscommunication or misunderstanding, potentially exacerbating conflicts or hindering effective communication. Through a comprehensive review of existing literature, online discourse analysis, and case studies, this research aims to shed light on the ways in which emojis influence the interpretation of textual messages and the potential challenges they pose to clear and accurate communication. The study concludes that as digital communication continues to be a primary mode of interaction, it is essential for users to recognize the potential for misinterpretation, prompting the need for increased emoji literacy and awareness.

How speaking versus writing to conversational agents shapes consumers’ choice and choice satisfaction

The use of conversational agents (e.g., chatbots) to simplify or aid consumers’ purchase decisions is on the rise. In designing those conversational agents, a key question for companies is whether and when it is advisable to enable voice-based rather than text-based interactions. Addressing this question, this study finds that matching consumers’ communication modality with product type (speaking about hedonic products; writing about utilitarian products) shapes consumers’ choice and increases choice satisfaction. Specifically, speaking fosters a feeling-based verbalizing focus, while writing triggers a reason-based focus. When this focus matches consumers’ mindset in evaluating the product type, preference fluency increases, thereby enhancing choice satisfaction. Accordingly, the authors provide insights into managing interactions with conversational agents more effectively to aid decision-making processes and increase choice satisfaction. Finally, they show that communication modality can serve as a strategic tool for low-equity brands to better compete with high-equity brands.

ChatGPT: Revolutionizing User Interactions with Advanced Natural Language Processing

Significant advancements in artificial intelligence (AI) have unexpectedly improved the standard of living globally. One recent development garnering attention is ChatGPT, a natural language processing (NLP) model created by OpenAI. ChatGPT combines OpenAI's GPT-2 language model with supervised and reinforcement learning techniques, leveraging the extensive language patterns in the GPT-3 corpus. This enables natural text-based interactions between users and AI systems, making it suitable for customer service applications and the creation of voice and text-based virtual assistants. ChatGPT offers features such as topic detection, sentiment detection, sentiment analysis, and the ability to generate multiple threads, enhancing users' understanding and enabling realistic interactions. This paper explores the challenges in AI development and proposed strategies to overcome them. It further examines how ChatGPT can enhance sectors such as chat e-commerce, education, entertainment, finance, health, news, and productivity, highlighting current use cases and potential future applications. The article emphasizes ChatGPT's potential to generate personalized content, making it a promising technology for improving user experiences and advancing AI-driven interactions.

The influence of task complexity and task modality on learners’ topic and turn management

Abstract Peer interaction is examined as an important indicator of performance in task-based language learning. However, little research has explored learners’ interactional competence under the influences of task factors. This study investigates the effects of task complexity and task modality on learners’ interactional competence in terms of topic management and turn management. Four tasks were designed – written-simple, written-complex, oral-simple, and oral-complex – and 40 Chinese EFL learners completed them in counterbalanced sequences. The results showed the significant influences of task complexity and task modality on learners’ topic and turn management. Task modality and complexity interactively influenced learners when they were expanding on topics in the role of the current speaker. Considering the cognitive demands of increasing complexity and differences between the two modalities, this paper discusses the implications of the findings for developing L2 interactional competence in speech- and text-based interactions.

Analysis of Patient Cues in Asynchronous Health Interactions: Pilot Study Combining Empathy Appraisal and Systemic Functional Linguistics.

Lifestyle-related diseases are among the leading causes of death and disability. Their rapid increase worldwide has called for low-cost, scalable solutions to promote health behavior changes. Digital health coaching has proved to be effective in delivering affordable, scalable programs to support lifestyle change. This approach increasingly relies on asynchronous text-based interventions to motivate and support behavior change. Although we know that empathy is a core element for a successful coach-user relationship and positive patient outcomes, we lack research on how this is realized in text-based interactions. Systemic functional linguistics (SFL) is a linguistic theory that may support the identification of empathy opportunities (EOs) in text-based interactions, as well as the reasoning behind patients' linguistic choices in their formulation. This study aims to determine whether empathy and SFL approaches correspond and complement each other satisfactorily to study text-based communication in a health coaching context. We sought to explore whether combining empathic assessment with SFL categories can provide a means to understand client-coach interactions in asynchronous text-based coaching interactions. We retrieved 148 text messages sent by 29 women who participated in a randomized trial of telecoaching for the prevention of gestational diabetes mellitus (GDM) and postnatal weight loss. We conducted a pilot study to identify users' explicit and implicit EOs and further investigated these statements using the SFL approach, focusing on the analysis of transitivity and thematic analysis. We identified 164 EOs present in 42.37% (3478/8209) of the word count in the corpus. These were mainly negative (n=90, 54.88%) and implicit (n=55, 60.00%). We distinguished opening, content and closing messages structures. Most of the wording was found in the content (n=7077, 86.21%) with a declarative structure (n=7084, 86.30%). Processes represented 22.4% (n=1839) of the corpus, with half being material (n=876, 10.67%) and mostly related to food and diet (n=196, 54.92%), physical activity (n=96, 26.89%), and lifestyle goals (n=40, 11.20%). Our findings show that empathy and SFL approaches are compatible. The results from our transitivity analysis reveal novel insights into the meanings of the users' EOs, such as their seek for help or praise, often missed by health care professionals (HCPs), and on the coach-user relationship. The absence of explicit EOs and direct questions could be attributed to low trust on or information about the coach's abilities. In the future, we will conduct further research to explore additional linguistic features and code coach messages. Australian New Zealand Clinical Trials Registry (ANZCTR) ACTRN12620001240932; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=380020.

TBSSvis: Visual analytics for Temporal Blind Source Separation

Temporal Blind Source Separation (TBSS) is used to obtain the true underlying processes from noisy temporal multivariate data, such as electrocardiograms. TBSS has similarities to Principal Component Analysis (PCA) as it separates the input data into univariate components and is applicable to suitable datasets from various domains, such as medicine, finance, or civil engineering. Despite TBSS’s broad applicability, the involved tasks are not well supported in current tools, which offer only text-based interactions and single static images. Analysts are limited in analyzing and comparing obtained results, which consist of diverse data such as matrices and sets of time series. Additionally, parameter settings have a big impact on separation performance, but as a consequence of improper tooling, analysts currently do not consider the whole parameter space. We propose to solve these problems by applying visual analytics (VA) principles. Our primary contribution is a design study for TBSS, which so far has not been explored by the visualization community. We developed a task abstraction and visualization design in a user-centered design process. Task-specific assembling of well-established visualization techniques and algorithms to gain insights in the TBSS processes is our secondary contribution. We present TBSSvis, an interactive web-based VA prototype, which we evaluated extensively in two interviews with five TBSS experts. Feedback and observations from these interviews show that TBSSvis supports the actual workflow and combination of interactive visualizations that facilitate the tasks involved in analyzing TBSS results.

Connecting over the internet: Establishing the therapeutic alliance in an internet-based treatment for depressed adolescents.

Internet-based treatments have been developed for youth mental health difficulties, with promising results. However, little is known about the features of therapeutic alliance, and how it is established and maintained, in text-based interactions between adolescents and therapists in internet-based treatments. This study uses data collected during a pilot evaluation of a psychodynamic internet-based therapy for depressed adolescents. The adolescents had instant-messaging chats with their therapists once a week, over 10weeks. The adolescents also rated the therapeutic alliance each week, using the Session Alliance Inventory. The present study uses qualitative methods to analyse transcripts of text-based communication between the young people and their therapists. The aim is to identify and describe the key features of therapeutic alliance, and reflect upon the implications for theory and clinical practice. Analysis identified three 'values' that may underpin a strong therapeutic alliance: togetherness, agency and hope. A number of therapist techniques were also found, which seemed to create a sense of these values during text-chat sessions. These findings are discussed, alongside implications for future research.

Feminist fire: embodiment and affect in managing conflict in digital feminist spaces

ABSTRACT Digital spaces are crucial in enabling participation in contemporary feminism and activism, as key sites through which feminist knowledges are dispersed, taken up, and debated. However, little is known about how feminist learning is practically enacted, and how the potential for conflict and debate in online feminist spaces are navigated and have implications for feminist pedagogies. Through a qualitative participatory study with self-described “digital feminists”, this article contributes to some of the first accounts of the role and significance of politicised embodiment in digital spaces, andempirically explores women and non-binary people’s experiences and understandings of digital feminist practice. Participants described that the “feminist fire” which propelled participation in digital spaces could be difficult to manage in online textual-only contexts, where careful communication was required to mitigate the absence of bodily cues such as tone of voice and facial expression. We argue that bodies matter differently in text-based online interactions and explore how feminists manage the parameters of online architectures and strong affective embodied responses to conflict and difficult conversations online. We argue a focus on bodies and embodied sensations are crucial for understanding how contemporary feminist learning is navigated in digital spaces.

Discursive strategies for addressing patients’ disalignment with diagnosis in online medical consultations in China

While online medical consultations (OMCs) have become increasingly popular, not least in times when epidemics make access to medical facilities difficult, research exploring the interactive value of OMC is still in its infancy. This study examines patients’ disalignment with speculative diagnosis and its management by doctors in OMC interactions, which to my best knowledge are not examined. From a discourse analytic perspective, this study adopts Du Bois’s notion of stance-taking to approach text-based interactions collected from a widely used OMC website in China. This study finds that patients’ disalignment is often based on hard evidence, which is different from the major findings of previous studies. When addressing such disalignment, doctors adopt varied discursive strategies, which are hardly mentioned in prior studies, in particular, strategies that address the affective aspect of patients’ disalignment. This study thus provides a different perspective on disalignment and its management in the clinical context.

Psychotherapy in the Digital Age: What We Can Learn From Interpersonal Psychotherapy.

The digital age poses new challenges for psychotherapy. More than four billion people worldwide use the Internet, and most of them engage with social media. Therapists are increasingly asked to help patients navigate the complex interface between online technology and relationships, but few are prepared to address this issue therapeutically. Interpersonal psychotherapy (IPT) is an evidence-based psychotherapy for depression and is focused on addressing interpersonal problems. The authors use the IPT framework to explore how therapists can discuss, during in-person sessions, the impact of technology on communication and relationships. The authors describe how therapists can preserve IPT's overarching goal of resolving interpersonal problems by adapting specific techniques to meet the needs of patients who routinely rely on technology to connect with others. Case vignettes illustrate techniques used to evaluate and modify technology-based communication, including problematic text-based interactions. Recommendations are provided for therapists seeking to meet the interpersonal needs of patients in the digital age.

Text as Data Methods for Education Research

Recent advances in computational linguistics and the social sciences have created new opportunities for the education research community to analyze relevant large-scale text data. However, the take-up of these advances in education research is still nascent. In this article, we review the recent automated text methods relevant to educational processes and determinants. We discuss both lexical-based and supervised methods, which expand the scale of text that researchers can analyze, as well as unsupervised methods, which allow researchers to discover new themes in their data. To illustrate these methods, we analyze the text interactions from a field experiment in the discussion forums of online classes. Our application shows that respondents provide less assistance and discuss slightly different topics with the randomized female posters, but respond with similar levels of positive and negative sentiment. These results demonstrate that combining qualitative coding with machine learning techniques can provide for a rich understanding of text-based interactions.

L2 interactional competence in asynchronous multiparty text-based communication: study of online collaborative writing

Web-based writing tools, which allow multiple writers to share and edit the same document, have attracted significant attention as computer-assisted language learning tools in the past decade. However, how L2 writers contribute to the shared document as a social action for interacting with other cowriters remains underexplored in L2 research. Inspired by conversation analysis, in this study, I conducted a moment-by-moment analysis of online, text-based (nonspeaking) asynchronous multiparty interactions consisting of two interactional modes: chat-based discussions and writing records displayed on the screen, with the aim of determining the methods employed by L2 learners to contribute writing changes over time. The data were taken from the online interactions of a group of nine or ten English as a foreign language university learners, who were asked to collaboratively write an essay in English, with the focus being on three learners to elucidate the changes in the methods used. The data analysis indicated that, over the course of the task, the participants used a greater number of methods to make their writing contribution to the entire essay more recognizable; these efforts included announcing the theme of the writing contribution, requesting corrections, and displaying alignment with an essay-in-progress by using a cohesive device in their writing, along with a variety of linguistic and semiotic repertoires. I also discuss the effects of the interlocutors on the online interactional competence of the individual learners.

Internet-Based Interventions for Problem Gambling: Scoping Review.

BackgroundThis study seeks to give an overview of academic research on internet-based interventions that are used to address problem gambling. The rate of treatment seeking has been demonstrated to be low across several research environments. This is in part because of the systemic barriers that treatment seekers face to accessing traditional face-to-face treatment. Making treatment resources for problem gambling available through the internet is one way to reduce the impact of those systemic barriers. The use of internet-based resources to address problem gambling has been growing, and a field of research evaluating it has developed as well. However, little has been done to summarize this collection of research.ObjectiveThis study aimed to provide a scoping review of the use of internet-based interventions for problem gambling treatment and prevention to provide an understanding of the current state of the field.MethodsA scoping review was performed for 6 peer-reviewed research databases (Web of Science, PsycINFO, Cumulative Index to Nursing and Allied Health Literature, MEDLINE, Social Science s, and Scopus) and 3 gray literature databases (MedEdPortal, Proquest: Dissertations, and OpenGrey). Article inclusion criteria were as follows: published over the 10-year period of 2007 to 2017, including an intervention for problem gambling, and involving the use of internet to deliver that intervention.ResultsA total of 27 articles were found that met the review criteria. Studies were found from several different areas, with particularly strong representation for Australia, New Zealand, and Scandinavia. Cognitive behavioral therapy was the most common form of internet-based intervention. Internet-based interventions were generally shown to be effective in reducing problem gambling scores and gambling behaviors. A wide range of interventions that made use of internet resources included text-based interactions with counselors and peers, automated personalized and normative feedback on gambling behaviors, and interactive cognitive behavioral therapies. A lack of diversity in samples, little comparison with face-to-face interventions, and issues of changes in the treatment dynamic are identified as areas that require further investigation.ConclusionsInternet-based interventions are a promising direction for treatment and prevention of problem gambling, particularly in reducing barriers to accessing professional help. The state of the current literature is sparse, and more research is needed for directly comparing internet-based interventions and their traditional counterparts.

Constructing Identities in Online Encounters

This article examines digital storytelling practices of 12-15-year-old students from Finland and Greece. In online settings, students construct virtual selves through video and text-based interactions with peers and, thus, perform identity work using English as the language of communication. This study examines digital storytelling as space of intertextuality where different speakers' utterances resignify the context of learning. The authors apply inductive analysis of interview data and a multimodal approach to digital stories as combinations of semiotic systems in order to link with a dynamic digital literacy. Findings indicate that the students use an impersonal, scientific-like style to explain how a chemical reaction happens in some stories. In others, they place the focus on human relationships with body language and gesture adding a personal style. However, rather than language, it is the way the story is performed and acted out that authenticates student work. This bears implications for both the teaching of English and the design of digital storytelling aiming for web-based peer exchanges.

Identity, voice and agency in two EAL doctoral writing contexts

Writing is central to the process of developing a scholarly identity and fundamental to the doctoral experience. Writing a PhD thesis in a second (L2) language involves considerable challenge since L2 writers need to master the academic literacy skills that support reading and writing complex texts. This paper explores that challenge in the writing experiences of two English as an Additional Language (EAL) doctoral candidates, Morena and Diego. The discussion draws on an online conversation about writing amongst Morena, Diego and Sara, a teacher of EAL writing and doctoral education researcher. Our conversation revolved around three central themes - identity, voice and agency – and their role in doctoral writing. After discussing related research, we present excerpts from our conversations that suggest how identity, voice and agency impacted on Morena and Diego’s writing experiences. We also consider affordances and constraints in Morena’s and Diego’s social and academic contexts and the opportunities they engaged with. We conclude by highlighting the challenges associated with developing a confident scholarly voice in a second language and recommend adopting a social approach to scholarly writing which supports text-based interactions amongst PhD peers, more experienced others and supervisors.

Textual Healing: Proof of Concept Study Examining the Impact of a Mindfulness Intervention on Smartphone Behavior

The digital age presents particular challenges to maintaining mindfulness, which has, in turn, has been proposed as a corrective agent to various negative consequences of habitual phone use. This study examined the feasibility, acceptability, and preliminary efficacy of an app-based intervention called Mindful Messaging, which was developed to increase overall mindfulness as well as mindfulness related to technology use and during text-based interactions. In a sample of 29 young adults, the use of Mindful Messaging resulted in a statistically significant increase in self-reported mindfulness and statistically significant decreases in drunk texting, texting while walking, and having accidents while walking and texting at follow-up relative to baseline. Effects of medium size were observed across outcomes (Cohen’s d ranged from 0.30 to 0.45). Non-significant reductions were also observed for emotional regulation difficulties, sexting and texting while driving, with small effect sizes. Participants’ use of an in-the-moment intervention for composing messages revealed that in comparison to pre-intervention texts, post-intervention texts conveyed increased honesty, vulnerability, self-awareness, empathy, perspective-taking, and concern about the recipient’s feelings. Feedback suggested the app was highly acceptable to users. Findings point to the potential health benefits of developing mobile interventions which induce mindfulness related to texting and other technology use.