Conversational Interface Research Articles

User preferences for ChatGPT-powered conversational interfaces versus traditional methods

This study examined user preferences for ChatGPT-powered conversational interfaces vs traditional techniques. The study collected data from 175 selected volunteers utilizing a survey questionnaire. Descriptive and inferential statistics were used to detect user preferences and compare them to the literature review. The study found that 70% of users chose ChatGPT-powered conversational interfaces over traditional techniques, citing convenience, efficiency, and personalization. Demographic data was explored. The participants were evenly distributed between male and female (50%) and aged 18 to 55 (mean = 35 years). This study affects ChatGPT and conversational AI development. The results indicate that users want to use these technologies in their daily lives. To improve ChatGPT, further study is needed in this area. However, this study's tiny sample size must be considered. To confirm these findings and investigate other factors affecting conversational interface user preferences, bigger and more diverse samples are needed.

<i>CovFakeBot</i>: a machine learning based chatbot using ensemble learning technique for COVID-19 fake news detection

The outbreak of the SARS-Cov-2 virus epidemic has been followed by a flood of misleading information on social media which is impacting millions of people every day. For this, we developed CovFakeBot, a conversational bot based on machine learning models to distinguish between fake and real news. The bot also provides the confidence score for the prediction that helps to ascertain trustworthiness of the news. Our system uses the COVID-19 tweet dataset and is trained over well-established state-of-the-art machine learning models. It is further optimised using ensemble learning methods for better accuracy. Results are evaluated using the accuracy and F1-score. We observed that ensemble learning using soft voting outperformed thus; we claim it as the best fit model. CovFakeBot is using WhatsApp Business API with Twilio to achieve conversational user interface. CovFakeBot will help the public to easily classify news as real or fake.

Architecture of project management web services based on integration with natural language processing modules

A method for intellectualizing project management web services based on integration with natural language processing modules is proposed. The supporting of high reliability, extensibility and flexibility of the interface of such systems is a necessary condition for the providing of effective tools for developers of software systems of various profiles. It is shown that a prevalent trend in software development is to increase the portability of software in order to ensure the possibility of using the same application in different runtime environments. The advantages of using the concept of “API-first” are highlighted. The features of the “API-first” web server architecture are considered, in which all requests for web services are executed through a single web API interface, and the resource-intensive web pages formation is transferred to a separate structure on the same host or to a separate web server. The advantages of using natural language processing tools to improve the efficiency and availability of project management web services are considered. Project management web service database structure is proposed. All the natural language processing data for the conversational interface consist of user intents list, entities collections list, entities (collocations or word sets). It will be stored within each external language processing web service in the appropriate format automatically. Examples of prototype business logic with functions for the internal and external API are shown. Most of the external natural language processing service handlers are closely related to this business logic.

Mental Health Assist and Diagnosis Conversational Interface using Logistic Regression Model for Emotion and Sentiment Analysis

The aim of this work was to create a fully functional AI-ML based conversational agent that behaves like a real time therapist which analyses the user’s emotion at every step and provides appropriate responses and feedback. AI chatbots, although fairly new to the domain of mental health, can help in destigmatizing seeking help, and are more easily accessible to everyone, at any time. Chatbots provide an effective way to communicate with a user and offer helpful emotional support in a more economical way. While making regular psychiatric visits often require a fixed duration/appointment which can be time consuming and is restricted to a fraction of the day, the proposed chatbot can keep track of your health on the go at any time. The application will have a self-healing kit suggesting various exercises, both mental and physical that the user may implement in his day-to-day life. The study below goes into further detail on the major insinuations for future chatbot agent design and assessment

Implementation of Embedded Unspecific Continuous English Speech Recognition Based on HMM

Background: To improve the usage of computers, a very important role is played by the Human-computer interaction through Natural Language Conversational Interfaces. Speech recognition technology allows the machine to understand human language. To achieve this function, a speech recognition algorithm is used. Methods: In order to realize the embedded speech recognition function based on HMM under the ARM platform, this paper, mainly based on the basic theoretical research of speech signals, establishes the HMM model, uses speech collection, recognition and other methods, simulates on MATLAB, and integrates the recognition system ported to ARM for debugging and running. Results: The research results show that the accuracy of HMM model experimental recognition can reach 98%, and the speed of speech recognition simulation on ARM is faster than speech recognition. The innovation of this paper is to make a comprehensive system introduction to embedded speech recognition from the perspective of embedded systems, and perform speech recognition simulation on MATLAB. Conclusion: The conclusion shows that the HMM-based embedded unspecific continuous English speech recognition system has high recognition accuracy and fast speed.

Towards Augmented Reality Driven Human-City Interaction: Current Research on Mobile Headsets and Future Challenges

Interaction design for Augmented Reality (AR) is gaining attention from both academia and industry. This survey discusses 260 articles (68.8% of articles published between 2015–2019) to review the field of human interaction in connected cities with emphasis on augmented reality-driven interaction. We provide an overview of Human-City Interaction and related technological approaches, followed by reviewing the latest trends of information visualization, constrained interfaces, and embodied interaction for AR headsets. We highlight under-explored issues in interface design and input techniques that warrant further research and conjecture that AR with complementary Conversational User Interfaces (CUIs) is a crucial enabler for ubiquitous interaction with immersive systems in smart cities. Our work helps researchers understand the current potential and future needs of AR in Human-City Interaction.

Using a Chatbot to Address Psychological Distress Among First Responders

<h3>Research Objectives</h3> Frontline COVID workers (doctors, nurses, paramedics, law enforcement officers, social workers) have been especially impacted by the pandemic (1). Stigma and fear of job loss often prevent help seeking (2,3). Evidence-based interventions exist but can be hard to navigate, limiting or delaying their timely uptake (4,5). Tools are needed to better identify people in need of treatment and provide care navigation that is timely and tailored to the individuals' needs, preferences, and level of distress and helps to circumnavigate stigma. To address this need, our team is conducting formative and acceptability and feasibility research to inform the development of a chatbot-a conversational interface (e.g. Amazon Alexa) using text or speech in a conversational, human-like manner to deliver information-to screen and refer COVID frontline workers to care. <h3>Design</h3> We are conducting interviews with 20 community behavioral health providers, advocates, law enforcement officers, and people living with mental illness. We are then asking 40 naïve users to test the prototype chatbot. Feedback from naïve users will be integrated into the fully functional chatbot. Simultaneously, we are conducting a national survey with adults to test the feasibility and acceptability of using chatbot technology for behavioral health screening and referral and examine correlates of mental health chatbot use (i.e. demographics, stigma, and technology readiness). <h3>Setting</h3> The setting of this study is online with frontline COVID responders and general community members. <h3>Participants</h3> 20 stakeholder interviews, testing with 40 naive users, and feasibility and acceptability testing with 500 national participants. <h3>Interventions</h3> We will ask participants to test a chatbot that will provide screening for distress (PHQ-9) and referral. The chatbot will require about 5 minutes of time to use. <h3>Main Outcome Measures</h3> Outcome measures related to feasibility and acceptability of the chatbot include willingness to engage with the chatbot and items from the Technology Acceptance Model. <h3>Results</h3> Findings will inform modifications to the chatbot and implementation planning. <h3>Conclusions</h3> This work will inform the use of chatbots for mental health screening and referral for various populations. <h3>Author(s) Disclosures</h3> No disclosures to report.

Chatbot breakthrough in the 2020s? An ethical reflection on the trend of automated consultations in health care

Many experts have emphasised that chatbots are not sufficiently mature to be able to technically diagnose patient conditions or replace the judgements of health professionals. The COVID-19 pandemic, however, has significantly increased the utilisation of health-oriented chatbots, for instance, as a conversational interface to answer questions, recommend care options, check symptoms and complete tasks such as booking appointments. In this paper, we take a proactive approach and consider how the emergence of task-oriented chatbots as partially automated consulting systems can influence clinical practices and expert–client relationships. We suggest the need for new approaches in professional ethics as the large-scale deployment of artificial intelligence may revolutionise professional decision-making and client–expert interaction in healthcare organisations. We argue that the implementation of chatbots amplifies the project of rationality and automation in clinical practice and alters traditional decision-making practices based on epistemic probability and prudence. This article contributes to the discussion on the ethical challenges posed by chatbots from the perspective of healthcare professional ethics.

Towards a model-driven approach for multiexperience AI-based user interfaces

Software systems start to include other types of interfaces beyond the “traditional” Graphical-User Interfaces (GUIs). In particular, Conversational User Interfaces (CUIs) such as chat and voice are becoming more and more popular. These new types of interfaces embed smart natural language processing components to understand user requests and respond to them. To provide an integrated user experience all the user interfaces in the system should be aware of each other and be able to collaborate. This is what is known as a multiexperience User Interface. Despite their many benefits, multiexperience UIs are challenging to build. So far CUIs are created as standalone components using a platform-dependent set of libraries and technologies. This raises significant integration, evolution and maintenance issues. This paper explores the application of model-driven techniques to the development of software applications embedding a multiexperience User Interface. We will discuss how raising the abstraction level at which these interfaces are defined enables a faster development and a better deployment and integration of each interface with the rest of the software system and the other interfaces with whom it may need to collaborate. In particular, we propose a new Domain Specific Language (DSL) for specifying several types of CUIs and show how this DSL can be part of an integrated modeling environment able to describe the interactions between the modeled CUIs and the other models of the system (including the models of the GUI). We will use the standard Interaction Flow Modeling Language (IFML) as an example “host” language.

Perceptions and reactions to conversational privacy initiated by a conversational user interface

In 2019, media reports raised awareness about privacy and security violations in Conversational User Interfaces (CUI) like Alexa, Siri and Google. Users report that they perceive CUI as creepy and that they are concerned about their privacy. The European General Data Protection Regulation (GDPR) and several other laws across the globe, give users the right to control processing of their data, for example by requesting deletion of their data and it gives them the right to obtain information about their data. Furthermore, GDPR and other laws advise for seamless communication of user rights, which, currently, is poorly implemented in CUI. We used a bespoke data collection interface to generate speaking chatbots and made them available as tasks on the crowd sourcing platform Mechanical Turk. With those chatbots we simulated how privacy can be communicated in a dialogue between user and machine. We find that conversational privacy can affect user perceptions of privacy and security positively. Moreover, user choices suggest that users are interested in obtaining information on their privacy and security in dialogue form. We discuss implications and limitations of this research.

REPRESENTATION AND APPLICATION OF DIGITAL STANDARDS USING KNOWLEDGE GRAPHS

AbstractStandards are an important source of knowledge in product development. Due to the increasing digitization of the product development process, standard development organizations aim to develop machine-actionable standards that automatically enforce operations in output devices. However, the current representation format in PDF or XML does not meet the requirements of machine-actionable standards. This paper examines existing approaches towards the representation of XML data in knowledge graphs and their transferability towards the domain of digital standards. Based on these approaches, the paper aims to develop and validate a concept for transferring standard content from XML format to a graph-based representation, using the example of formulas. For this purpose, a concept for the automatic identification, extraction and modeling of formulas will be presented. Afterwards, the concept is validated using the example of DIN ISO 281 whereas a chatbot application serves as conversational user interface. It is proven, that knowledge graphs are suitable for the representation of machine-actionable standard content. Future work will investigate the abstraction towards a general approach as well as further information objects of standards.

Why Real Citizens Would Turn to Artificial Leaders

Governments are increasingly using artificial intelligence to improve workflows and services. Applications range from predicting climate change, crime, and earthquakes to flu outbreaks, low air quality, and tax fraud. Artificial agents are already having an impact on eldercare, education, and open government, enabling users to complete procedures through a conversational interface. Whether replacing humans or assisting them, they are the technological fix of our times. In two experiments and a follow-up study, we investigate factors that influence the acceptance of artificial agents in positions of power, using attachment theory and disappointment theory as explanatory models. We found that when the state of the world provokes anxiety, citizens perceive artificial agents as a reliable proxy to replace human leaders. Moreover, people accept artificial agents as decision-makers in politics and security more willingly when they deem their leaders or government to be untrustworthy, disappointing, or immoral. Finally, we discuss these results with respect to theories of technology acceptance and the delegation of duties and prerogatives.

Teaching Tech to Talk: K-12 Conversational Artificial Intelligence Literacy Curriculum and Development Tools

With children talking to smart-speakers, smart-phones and even smart-microwaves daily, it is increasingly important to educate students on how these agents work—from underlying mechanisms to societal implications. Researchers are developing tools and curriculum to teach K-12 students broadly about artificial intelligence (AI); however, few studies have evaluated these tools with respect to AI-specific learning outcomes, and even fewer have addressed student learning about AI-based conversational agents. We evaluated our Conversational Agent Interface for MIT App Inventor and workshop curriculum with respect to 8 AI competencies from the literature. Furthermore, we analyze teacher (n=9) and student (n=47) feedback from workshops with the interface and recommend that future work (1) leverages design considerations to optimize engagement, (2) collaborates with teachers, and (3) addresses a range of student abilities through pacing and opportunities for extension. We found evidence for student understanding of all 8 competencies, with the most difficult concepts being AI ethics and machine learning. We recommend emphasizing these topics in future curricula.

Designing a Chat-bot for College Information using Information Retrieval and Automatic Text Summarization Techniques

Background:: In the era of information overload it is very difficult for a human reader to make sense of the vast information available on the internet quickly. Even for a specific domain like a college or university website, it may be difficult for a user to browse through all the links to quickly get the relevant answers. Objective:: In this scenario, the design of a chat-bot which can answer questions related to college information and compare between colleges will be very useful and novel. Methods:: In this paper, a novel conversational interface chat-bot application with information retrieval and text summarization skill is designed and implemented. Firstly, this chat-bot has a simple dialog skill; when it can understand the user query intent, it responds from the stored collection of answers. Secondly, for unknown queries, this chat-bot can search the internet, and then perform text summarization using advanced techniques of natural language processing (NLP) and text mining (TM). Results:: The advancement of NLP capability of information retrieval and text summarization using machine learning techniques of Latent Semantic Analysis (LSI), Latent Dirichlet Allocation (LDA), Word2Vec, Global Vector (GloVe) and TextRank is reviewed and compared in this paper first before implementing them for the chat-bot design. This chat-bot improves user experience tremendously by getting answers to specific queries concisely which takes less time than to read the entire document. Students, parents and faculty can get the answers for a variety of information like admission criteria, fees, course offerings, notice board, attendance, grades, placements, faculty profile, research papers, patents, etc. more efficiently. Conclusion:: The purpose of this paper was to follow the advancement in NLP technologies and implement them in a novel application.

대화형 인터페이스 진화에 따른 모달리티 유형별 사례 연구

대화형 인터페이스 진화에 따른 모달리티 유형별 사례 연구

ARTIFICIAL INTELLIGENCE AS A HUMAN SUBSTITUTION? CUSTOMER'S PERCEPTION OF THE CONVERSATIONAL USER INTERFACE IN BANKING INDUSTRY BASED ON UTAUT CONCEPT

This study aims to analyze the differences in perceptions between customers of Bank Rakyat Indonesia, Bank Negara Indonesia, and Bank Mandiri regarding the use of the conversational user interface owned by each bank. This study used 58 respondents. By using the Kruskal Wallis technique, it can be concluded that there are differences in perceptions between customers of Bank Rakyat Indonesia, Bank Negara Indonesia and Bank Mandiri who interact using the conversational user interface facility. Even though it is easy to use, the absence of recommendations from the community and family as well as concerns that the chatbot is unable to provide the right information and solutions can have implications for the reluctance of customers to use these facilities in the future

Cognitive analysis in sports: Supporting match analysis and scouting through artificial intelligence

AbstractIn elite sports, there is an opportunity to take advantage of rich and detailed datasets generated across multiple threads of the sporting business. Challenges currently exist due to time constraints to analyse the data, as well as the quantity and variety of data available to assess. Artificial Intelligence (AI) techniques can be a valuable asset in assisting decision makers in tackling such challenges, but deep AI skills are generally not held by those with rich experience in sporting domains. Here, we describe how certain commonly available AI services can be used to provide analytic assistance to sports experts in exploring, and gaining insights from, typical data sources. In particular, we focus on the use of Natural Language Processing and Conversational Interfaces to provide users with an intuitive and time‐saving toolkit to explore their datasets and the conclusions arising from analytics performed on them. We show the benefit of presenting powerful AI and analytic techniques to domain experts, showing the potential for impact not only at the elite level of sports, where AI and analytic capabilities may be more available, but also at a more grass‐roots level where there is generally little access to specialist resources. The work described in this paper was trialled with Leatherhead Football Club, a semi‐professional team that, at the time, were based in the English 7th tier of football.

Managing non-trivial internet-of-things systems with conversational assistants: A prototype and a feasibility experiment

Internet-of-Things has reshaped the way people interact with their surroundings and automatize the once manual actions. In a smart home, controlling the Internet-connected lights is as simple as speaking to a nearby conversational assistant. However, specifying interaction rules, such as making the lamp turn on at specific times or when someone enters the space is not a straightforward task. The complexity of doing such increases as the number and variety of devices increases, along with the number of household members. Thus, managing such systems becomes a problem, including finding out why something has happened. This issue lead to the birth of several low-code development solutions that allow users to define rules to their systems, at the cost of discarding the easiness and accessibility of voice interaction. In this paper we extend the previous published work on Jarvis [1], a conversational interface to manage IoT systems that attempts to address these issues by allowing users to specify time-based rules, use contextual awareness for more natural interactions, provide event management and support causality queries. A proof-of-concept is presented, detailing its architecture and natural language processing capabilities. A feasibility experiment was carried with mostly non-technical participants, providing evidence that Jarvis is intuitive enough to be used by common end-users, with participants showcasing an overall preference by conversational assistants over visual low-code solutions.

Multi agent-based framework for interactive learning system with conversational user interface for visually and speech impaired

The purpose of this research article is to illustrate the role of Conversational User Interface to foster inclusive education among the Speech Impaired People (SIP) and the Visually Impaired People (VIP). The multiagent framework on “Conversational User Interface for interactive learning” will throw light on the role of the host and the learner in communicating and facilitating knowledge with each other. The article has been built after the in-depth exploration of various sources, which were handpicked for the study. This multiagent model can be put into implementation in the education industry. The scope of the study extends only to SIP’s and VIP’s because of their growing numbers across the globe, and yet they are deprived of formal education. The Conversational User interface can be used to bridge the gap, especially with the advancement of technologies such as VUI, MUI, WUI, BOTs, etc., for the VIPs and SIPs.

Control of Smart house sensors using Google Assistant

As a result of the research, a working model was created by smart home devices and the Internet of Things using a voice interface. Integrated Google Assistant, Dialogflow, PHP and MQTT. Voice interfaces are closely related not only to the use of smartphones, but also to wearable electronics, autonomous control, speaker speakers and even games. In turn, the Internet of Things today is not only a concept, but also a real movement with its technologies and protocols. Their variety and use of open technologies allows you to flexibly choose the tools for the project you need, taking into account its specifics. Smart lighting control systems are very popular because of the convenience of such solutions (remote on and off, increase and decrease brightness), the ability to collect and analyze data, the ability to make decisions depending on the ratio of external sensors and events. Google Assistant is an artificial intelligence-powered virtual assistant developed by Google that is primarily available on mobile and smart home devices. Unlike the company’s previous virtual assistant, Google Now, the Google Assistant can engage in two-way conversations. Dialogflow is a natural language understanding platform used to design and integrate a conversational user interface into mobile apps, web applications, devices, bots, interactive voice response systems and related uses. The ESP8266 is a low-cost Wi-Fi microchip, with a full TCP/IP stack and microcontroller capability, produced by Espressif Systems in Shanghai, China. The Message Queuing Telemetry Transport (MQTT) is a lightweight, publish-subscribe network protocol that transports messages between devices. The protocol usually runs over TCP/IP; however, any network protocol that provides ordered, lossless, bi-directional connections can support MQTT. It is designed for connections with remote locations where a «small code footprint» is required or the network bandwidth is limited.