Search

Visual Question Answering (VQA) systems have achieved remarkable advancements by combining text-based question answering with image analysis. This integration has resulted in the creating of machines that can comprehend and address questions related to visual content. Despite these technological developments, a notable lack of VQA solutions specifically designed for the Arabic language remains. This gap persists even with the significant progress made in deep learning techniques and the development of Large Language models (LLMs). Our research introduces ArabicQuest, an innovative chatbot designed specifically for Arabic-speaking users. ArabicQuest utilizes the LLaVa Large Language Model, a dedicated translation model, and reinforcement learning from human feedback (RLHF) to effectively integrate Arabic text with visual data. Through Telegram's application API, ArabicQuest offers a seamless user interface to ask image-based questions. The proposed pipeline continuously improves its accuracy and relevance by incorporating user feedback, achieving an accuracy of 86%. ArabicQuest is trained and evaluated on various datasets, including Visual Genome, RSVQA, and ChartsQA, to ensure robust performance. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to develop a better understanding about the benefits that can be realized after implementing voice-based chatbot technologies in banks. Furthermore, this paper aims to investigate the challenges faced by organizations when implementing such technologies. This study followed a qualitative approach where semi-structured interviews were conducted with experts from mid to senior managerial levels working in a leading bank operating in Jordan and had implemented the voice-based chatbot technology. Implementing voice-based chatbot technology for the first time in a Jordanian bank has positively impacted the growth of the bank, increased customers satisfaction, and added a competitive advantage value to the bank. On the other side, different challenges faced the bank when it implemented this technology like issues related to security, compliance, integration, and infrastructure limitations. This paper can be considered in the foremost research conducted to investigate the implementation of AI-based chatbot in Jordanian banks. It demonstrated the benefits and challenges resulting from performing digital innovations introduced as innovative services in the banking sector that can inform the experience to other banks interested to implement such technologies. [ABSTRACT FROM AUTHOR]

Universities gain a competitive advantage by deliberately improving overall service, student, faculty, and staff experience, leading to attractiveness, retention, and improved outcomes. Quality services are achieved partly by addressing employee satisfaction, specifically in the work environment. This paper presents a prototype study of a virtual university support agent, a system grounded in a Large Language Model (LLM) engineered to address inquiries from university students, faculty and staff related to the student handbook. The study investigates the integration of generative artificial intelligence and natural conversation properties inherent in LLMs to overcome customer service shortcomings identified in previous chatbot applications. The LLMs' susceptibility to 'hallucination' is mitigated through a combined approach of few-shot learning and chain of thought libraries in the training phase. The information core of this system comprises student handbook PDF files, from which an algorithm extracts and structures data to be utilized by the LLM. As a result, the university support agent facilitates a viable Q&A interface for students, faculty, and administrators to inquire about university guidelines and policies. [ABSTRACT FROM AUTHOR]

The weaponization of artificial intelligence (AI) and machine learning (ML) models in cybersecurity is a growing concern, with cybercriminal organizations and nation-states exploiting their weaknesses. The Microsoft "Tay" chatbot incident exemplifies the risks of weaponized AI, as it displayed sexist and racist behaviors due to malicious data inputs. The researcher examined 21 academic studies on AI weaponization and AI-driven cyberattacks in this systematic review. This work, a systematic review, concludes with an in-depth understanding of the scale and scope of using AI as a cyber weapon. The findings revealed that more research is necessary on weaponizing AI for offensive cybersecurity applications and the following key observations (a) a connection between AI weaponization and countermeasures, (b) AI's role in enhancing cybersecurity defenses, (c) AI weaponization offering mitigation strategies for protecting digital assets and infrastructure, and (d) AI-driven attacks exploiting vulnerabilities, enabling automation and scalability, facilitating data poisoning and manipulation, improving social engineering, and augmenting evasion obfuscation. This study contributes to a better understanding of AI weaponization and aids researchers in synthesizing current literature on the topic. [ABSTRACT FROM AUTHOR]

Chatbots have revolutionized human-computer interactions in various fields, driven by advancements in Artificial Intelligence. Similarly, gamification techniques have emerged as innovative methods to engage users and enhance experiences. This paper presents an analysis of the trends, applications, methods, and challenges associated with chatbots, with a particular emphasis on their capability to generate customized gamification solutions for industrial 5.0 environments. These environments are characterized by the increased use of technologies - such as Virtual and Augmented Reality - driven by the digital transformation of Industry 4.0 (I4.0). As Industry 5.0 (I5.0) builds upon I4.0, emphasizing human-technology collaborations and coexistence of humans and advanced technologies, the role of chatbots and gamification in this context becomes even more compelling. Within this research, various gamification applications and chatbot architectures, ranging from rule-based to generative models, are identified to assess their suitability for the specific needs of industrial 5.0 environments. The primary objective of this study is to explore the potential of leveraging chatbot assistance to enhance gamification experiences by considering employee specific characteristics, workplace technologies, and other relevant factors. By examining the advancements and obstacles in this field, this study aims to explore the potential of chatbots for increasing the effectiveness of gamification strategies. This integration is anticipated to lead to more immersive and personalized experiences, increased employee satisfaction, positive work environment, and enhanced skill development and performance. However, several challenges such as security, user acceptance and the need for continuous adaptation must be addressed to ensure the successful implementation of chatbot-driven gamification in I5.0 environments. The navigation through these challenges holds the key to unlocking the full potential of these transformative technologies and methods, paving the way for a more engaging and enriching work environment. [ABSTRACT FROM AUTHOR]

A key development towards enhancing computer-human interaction is emotion recognition. This publication describes a technique called EmoCNN, which uses deep learning techniques to precisely identify and classify human emotions, emphasizing improving model performance using different optimizers. Our research intends to contribute to the creation of more effective systems that improve computer-human interaction by solving the problems associated with emotion recognition. By bridging the gap between humans and robots, accurate emotion detection enables systems to perceive emotions for customized and responsive interactions. AI-powered assistants, chatbots, and social robots all benefit from emotion recognition by providing more responsive, empathic and interesting user experiences. Emotion-aware technologies can also enhance user feedback analysis, human-centered design, and monitoring of mental health. Using a human emotion detection dataset, we carried out comprehensive experiments focusing on the happy, sad, and neutral emotion classes. Constructing a customized EmoCNN model with convolutional layers, a hidden layer, ReLU activation, and max-pooling was the focus of our computational work. We investigated various optimizers and evaluated how they affected accuracy, convergence speed and loss minimization. The results demonstrated that the EmoCNN model, which had been trained using the Adam optimizer, gave the best accuracy in distinguishing between emotions. Our paper provides a comparative analysis, highlighting the superiority of EmoCNN over existing models, showcasing its ability to achieve higher validation accuracy (89%) and more efficient emotion recognition when compared to previous approaches with minimal loss. Our research advances the field of emotional computing by demonstrating how well EmoCNN can identify and categorizes various human emotions. This discovery has significant ramifications for the creation of emotion-aware computers, which can better understand and react to human emotions, enhancing computer-human interaction. [ABSTRACT FROM AUTHOR]

Mental health therapy plays a crucial role in addressing the growing challenges of mental health disorders. However, barriers such as limited accessibility and social stigma often hinder individuals from seeking timely and effective support. Advancement in the field of Artificial Intelligence (AI) and Natural Language Processing (NLP) has enabled the development of Chatbots which can simulate counseling conversations and provide support to those who seek help. However, existing chatbots often lack contextual understanding, limit user responses to multiple-choice questions, and face challenges in generating human-like responses. In this work, we present an Intelligent Conversational Agent using Reinforcement Learning with Human Feedback (RLHF) for mental health therapy support. The proposed system employs reinforcement learning to optimize its responses and adapts its conversational strategies to better understand user's responses, analyze the emotions expressed, and provide personalized therapeutic interventions to enhance Mental Health Therapy. [ABSTRACT FROM AUTHOR]

Immunization is a way to increase a person's immunity, to prevent exposure to Preventable Diseases by Vaccine. There are two types of immunizations that are given when a baby is born: basic and optional. Basic immunization is given when the child is 0-24 months old. Optional immunizations are immunizations that are not included in government immunization programs but are important for infants in Indonesia since Indonesia has several endemics. Currently, immunizations that have been carried out in Indonesia are still experiencing some obstacles. Where the parents of the baby still lack knowledge about basic and optional immunizations. In addition, parents still lack information about the right time to immunize their child. This research aims to develop a reminder system for parents through two approaches: a reminder system and a chatbot to give information related immunization. The reminder system is web-based and uses WhatsApp gateway to provide reminders to parents. The creation of this system starts from extracting knowledge about immunization supplied by Indonesian Pediatric Association (IDAI) which modeled into rules. Then, an immunization reminder schedule will be given through WhatsApp app to the parents at the right time (can be set 1-2 days before) based on these rules. Testing on the system is carried out using four test cases and validated by a pediatrician. The system can help parents remember immunization schedules through WhatsApp and can find out information about the immunizations through chatbot with Telegram app. [ABSTRACT FROM AUTHOR]

Epilepsy is a brain disorder that can affect people of all ages which is one of the most common neurological disorders affecting around 50 million individuals. Healthcare Chatbots schedule appointments, respond to patient inquiries, and offer relevant information, freeing medical staff to handle life crises. This paper implements a chatbot for epilepsy patients to increase awareness about epilepsy. Patients may easily access this AI-based healthcare chatbot whenever they have queries regarding precautions to be taken by epilepsy patients. Chatbot uses a rich set of epilepsy-related datasets collected from trusted websites which are preprocessed with NLP techniques to prepare the data for model inputs.DNN, LSTM, and RNN models are created and evaluated to produce answers to user queries related to possible precautions to avoid seizures, safety measures to be taken by patients with seizure history, etc. Evaluation of models shows that the RNN model generates more accurate answers with 94% accuracy. Finally, the epilepsy question answering Chatbot for precaution is concluded with the RNN model. [ABSTRACT FROM AUTHOR]

Hospitals serve as critical hubs for global healthcare, offering essential medical services. However, a pressing issue is the lack of 24/7 medical facilities in rural areas, particularly during the overnight hours. To bridge this gap, we propose the Robotic Medical Support ChatBot (RMSCB) system. This innovative online platform leverages machine learning to autonomously predict medical diagnoses and provide temporary solutions, accessible at any time. The RMSCB system comprises three key stages: pre-processing, training, and classification. In the pre-processing stage, relevant keywords are extracted using the Pre-Fixed Stopping Words Model (PFSWM). The training stage categorizes pre-processed questions into classes based on the Pre-Fixed Class Label Model (PFCLM), associating medical solutions via the Pre-Fixed Answer and Question Model (PFAQM). In the classification stage, the RMSCB processes clinical questions from patients via mobile or personal systems, mapping and identifying solutions based on probability. Experimental results demonstrate the efficacy of the RMSCB system, offering timely first aid medication information and alleviating the need for immediate physician consultation. This technological solution addresses critical healthcare gaps, especially in regions with limited access to continuous medical services. [ABSTRACT FROM AUTHOR]

Today, the tourism industry is significantly impacted by mobile applications leveraging Artificial Intelligence (AI) and Natural Language Processing (NLP) to enhance tourists' experiences before, during, and after their visits. This technological convergence has given rise to Smart Tourism Destinations (STDs). However, efficiently integrating these functionalities into mobile apps poses a major challenge, leading to the emergence of chatbots. Companies like IBM, Google, Microsoft, and Amazon offer tools such as Watson, Bot Framework, Dialogflow, and Amazon Lex for their development. Nevertheless, creating chatbots remains intricate, demanding expertise in software development and AI, along with associated costs related to NLP service providers. Additionally, employing an appropriate modeling language is crucial for designing a chatbot. At this juncture, the concepts of software factories and Domain-Specific Languages (DSLs) become indispensable. These innovative approaches provide solutions for addressing these complex challenges. Software factories automate the development process, expediting chatbot creation while ensuring consistency. Simultaneously, DSLs furnish tools for accurately modeling and articulating the specific requirements of smart tourism, simplifying the development of tailor-made chatbots suited to this domain. This article introduces a model-driven approach for a DSL aimed at offering an abstract, high-level representation of the various aspects of chatbots within the context of an intelligent tourism mobile application. [ABSTRACT FROM AUTHOR]

The digitalization of businesses proves to create more opportunities for big and smaller businesses to expand their businesses through the internet. Customer engagement is more prevalent due to internet accessibility making businesses scramble for solutions to reach out to more customers and retain them. Chatbots have been the most popular solution chosen by businesses for e-commerce. The technological advancements in Chatbots itself have made chatbots more humanlike, accurate and easier to create. This paper presents the existing implementations of chatbots and the usages. Chatbot technology isn't good enough to allow even big businesses to develop a 100% accurate chatbot. However, chatbot technology has advanced enough in the form of chatbot platforms. Chatbot platforms provide smaller businesses an easy way to create and implement chatbots to their business without needing or with minimal knowledge of coding. Which means everyone has an opportunity to create their own chatbot for their needs with condition that they are willing to put some time in it compared to before were businesses need experts to develop a chatbot from scratch. [ABSTRACT FROM AUTHOR]

The development of artificial intelligence systems has resulted in various AI products including ChatGPT, which is a new product classified as a chatbot. This research aims to ensure that text generation systems such as ChatGPT open AI have the best level of quality and usability and are able to provide a satisfying experience for users. To measure and evaluate the effectiveness, efficiency and user satisfaction of the ChatGPT platform, researchers used the System Usability Scale (SUS) method. This data collection was carried out using an online questionnaire. After the collected data has been tested for validity and reliability, the researchers then analyzed the data results. From the results of the research conducted, the SUS value of the ChatGPT platform is 67.44. This score is included in the marginal high category of class D, with a reasonable or sufficient interpretation. With the results of the analysis per question item, it shows that users tend to agree that the system runs quite effectively, efficiently, well and is easy to understand. Although ChatGPT is able to perform tasks or commands well. However, it should be noted that not all information loaded by ChatGPT is presented in a complete, current and correct manner. This is because the information presented by ChatGPT is only limited to 2021. Because ChatGPT is a new technology and is still under development, further researchers are expected to test other features or ChatGPT to ensure the stability and reliability of the entire ChatGPT system using other research methods. [ABSTRACT FROM AUTHOR]

We propose a web-based platform of integrated intelligent agents that incorporates multiple Functional Mock-up Units (FMUs) and surrogate modelling techniques. In this platform, each FMU envelops a stand-alone simulation component that represents an aquaculture system, such as the fish growth model, water quality model, and fish behavior model. Some FMUs may be computationally expensive to simulate or have different time step intervals, making integration with other FMUs difficult. To address these challenges, we employed surrogate models to substitute the more computationally expensive models. In this work, surrogate models are trained using simulation data and selected based on robustness analysis to ensure the overall system input-output reliability. The platform also includes a Chatbot component utilizing natural language processing and decision-making techniques to interpret user requests and provide tailored FMU configurations, enhancing the user simulation experience. Overall, the proposed platform provides a comprehensive and Efficient approach to modelling and simulating complex systems such as fish farms. Robustness analysis ensures the platform's accuracy and reliability, while the user-friendly interface enables easy tailored experimentation. By providing a framework for exploring the potential of aquaculture as a key source of food and income, the proposed platform represents a valuable interactive simulation tool for researchers, policymakers, and industry professionals seeking to improve the sustainability, efficiency, and economic viability of the aquaculture industry. [ABSTRACT FROM AUTHOR]

The e-commerce market has been growing dynamically for years. This is due to the changing habits of consumers and the progressing digitization of life. Digital transformation forces companies to invest in new technologies and change existing sales models. Among the many trends that operate in e-commerce, there are a few that may play a significant role in the coming years. the aim of the article is to identify the trends and IT solutions for e-commerce and discuss their importance in the development of this sector. The research that was carried out was based on a throughout review of the professional literature and specialist reports. The research points out that acting in accordance with the latest trends includes placing the customer and his needs at the center of activities carried out by e-sellers. To achieve this, it is worth using chatbots, sending personalized newsletters, offering modern payment methods, and acting in accordance with ecology. In these activities, it is necessary to use new technologies and solutions, such as Big Data, the Internet of Things or Artificial Intelligence. It is indisputable that in such a turbulent environment only those enterprises that can constantly adapt to change have a chance of survival. [ABSTRACT FROM AUTHOR]

The development of e-commerce is determined by several factors, including digital transformation, the COVID-19 pandemic, changing consumer behavior and product innovations that appear on the market, including ChatGPT which is one of the latest innovations in the field of artificial intelligence and which offers many opportunities for the e-commerce industry. Thus, the main aim of the paper is answering to the research question how ChatGPT can help e-commerce stores improve their customer communication, increase sales conversions, customer service, and build loyalty? In the article, a simple case study of a conversation between authors and an artificial intelligence-based chatbot ChatGPT was introduced. Several questions were asked related to e-commerce sphere. [ABSTRACT FROM AUTHOR]

In university-level education, the computer network is a mandatory course for computer science and engineering majors. A computer network course provides theoretical and hands-on foundations for network connectivity, network topologies, internet protocols, networking devices, and gateways. In the traditional classroom, students face challenges in gaining essential knowledge and self-efficacy. Teachers face challenges in assessing students' quality of knowledge due to the abundance of online computer science teaching resources. Chatbot technologies have the potential to overcome these challenges and enhance essential knowledge and self-efficacy. However, the argument remains whether a course-specific standard chatbot or a generalizable chatbot could produce high-quality answers. Therefore, in this paper, we research 1) to what extent does using chatbots improve higher education students' essential knowledge of computers network? and 2) to what extent does using chatbots improve the self-efficacy of higher education students? Our first insight indicates that groundbreaking generalizable chatbots such as You and ChatGPT produce rather detailed answers to the questions associated with computer network courses, but those answers may not be the model answers that teachers expect from the students. Hence, research-based course-specific standard chatbots are required to teach computer network topics effectively. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) empowers Business Intelligence (BI) by enhancing data analysis, automating data integration, enabling predictive analytics, providing natural language interfaces, detecting anomalies, delivering personalized recommendations, and enhancing data visualization. AI-driven systems process large datasets, identify patterns, and extract valuable insights. They automate data integration, cleansing, and transformation. Predictive analytics forecasts future trends, while natural language interfaces make data access easier. This paper gives an overview of the perspectives of intelligent empowerment of BI by AI. It focuses on presenting the ways AI can complement or even enhance the different processes of BI systems used for driving decision-making. Therefore, contextualizing the use of AI in business empowerment, we analyzed the perspectives of making intelligent empowerment of BI based on AI. We further exhibit a flowchart showing how AI Chatbots can assist BI processes to achieve the highest level of contextual autonomy and creative capability with continual improvement. [ABSTRACT FROM AUTHOR]

When it comes to university life, university services, and communication with staff, things can be difficult and complicated, especially for newly joined students. This paper provides TU-Smart Services application which focus on filling the gap between students, university services and staff with in Ta'if University (TU). Our App consists of four main features: Cody, a smart conversational chatbot agent, an interactive campus map to direct students within the campus, digital wallet to show all the university IDs, and Academic advisor communication session. Cody has been developed to ease the communication and transactions between students, university services and staff, while interactive campus map has been developed to guide students in the university campus. This project aims to increase the benefits for Taif University students and visitors to make their university services more efficient and reliable. [ABSTRACT FROM AUTHOR]

The COVID-19 increased the importance of patient's continuous assessment of health outcomes. In 2021 WHO proposed some Digital Health guidelines arguing that health systems should consider the use of emergent technologies in health care services. This health environment is providing intelligent systems to guide patients in self-care. One example of that is the chatbot which is, a conversational agent that have been assuming an important role in how to improve health knowledge, reducing the incidence of diseases and avoiding new ones. Pregnant women are a profile where the self-care referred before is a critical issue. Prenatal services reveal to be an important part of the care process where most complications for that women happen. This article aims to comprehend how pregnant women interact with a conversational agent and how relevant this Digital Health tool is for primary health care services. The study presents the process and results of a systematic literature review about the user experience with of a chatbot in pregnant women self-care context; a summary of GISSA intelligent chatbot development including the use of technologies such as DialogFlow; and the process and results of GISSA usability evaluation in research field. Results show that a small amount of articles was gathered and the chatbot as a tool is a relevant opportunity for primary care health services in Brasil. [ABSTRACT FROM AUTHOR]

In recent times, banks have increasingly started using chatbots to offer round-the-clock customer service. However, customers experience with this type of technology is not well understood. The aim of this study was to get an in-depth understanding of factors affecting customer experience with a banking chatbot. Eight participants interacted with a real-life banking chatbot to complete a simple task (order a credit/debit card) and a complex task (apply for a housing loan). Semi-structured interviews were then conducted to examine chatbot-related factors (ease of use, miscommunication errors and human-likeness) and user-related factors (perceptions, future behaviors). The findings indicate that the human-like factors like a human personality, use of emojis, willingness to help, and polite communication style, have a positive impact of customer experience with banking chatbots. The chatbot's ability to understand questions was a critical factor. Miscommunication errors have negative impact, especially when the task is a simple one. Takeaway from this study is that banks should inform customers about the limits of the chatbot's abilities. In addition, they should communicate that the chatbot is safe to use for complex tasks. Successful development and implementation of chatbots for customer service require a customer centric approach from banks. [ABSTRACT FROM AUTHOR]

The article aims to show the role (benefits and challenges) of AI-powered digital marketing tools for marketers in the age of digital transformation. The considerations were related to the Polish market and a case study of LPP, a Polish clothing retailer. The starting point for this study was the analysis of the literature on the concept of artificial intelligence (AI) with reference to digital marketing. In the next steps, the results of the research on the Polish market conducted by the Digital Poland Foundation and presented in the report entitled "State of Polish AI 2021" were reviewed, and an application case study of the largest Polish clothing company – LPP – was conducted. The study is of an introductory and exploratory nature. It recognises the significant role of AI in digital transformation in the context of digital marketing in the Polish market. The implementation of solutions based on artificial intelligence algorithms, such as the Google Cloud, analytical platform and data repository, e-commerce infrastructure, chatbot, Genesys PureCloud, Google Dialogflow and the AI-based function in the PSIwms Warehouse Management System in LPP's distribution centre significantly improves the efficiency of online order processing without compromising the quality of products and order fulfilment time. By applying a case study analysis, the importance of AI-based tools in the digital transformation process, including digital marketing, in the Polish market was demonstrated. Marketers, including CMOs, were shown the benefits of applying AI-related technological solutions in the field of e-commerce optimisation and customer service. [ABSTRACT FROM AUTHOR]

The world was taken aback when the Covid-19 pandemic hit in 2019. Ever since precautions have been taken to prevent the spreading or mutating of the virus, but the virus still keeps spreading and mutating. Scientists predict that the virus is going to stay for a long time but with reduced effectiveness. Recognizing the symptoms of the virus is essential in order to provide proper treatment for the virus. Visiting hospitals for consultation becomes quite difficult when people are supposed to maintain social distancing. Recently neural network generative models have shown impressive abilities in developing chatbots. However, using these neural network generative models that lack the required Covid specific knowledge to develop a Covid consulting system makes them difficult to be scaled. In order to bridge the gap between patients and a limited number of doctors we have proposed a Covid consulting agent by integrating the medical knowledge of Covid-19 with the neural network generative models. This system will automatically scan patient's dialogues seeking for a consultation to recognize the symptoms for Covid-19. The transformer and pretrained systems of BERT-GPT and GPT were fine-tuned CovidDialog-English dataset to generate responses for Covid-19 which were doctor-like and clinically meaningful to further solve the problem of the surging demand for medical consultations compared to the limited number of medical professionals. The results are evaluated and compared using multiple evaluation metrics which are NIST- n , perplexity, BLEU- n , METEOR, Entropy- n and Dist- n. In this paper, we also hope to prove that the results obtained from the automated dialogue systems were significantly similar to human evaluation. Furthermore, the evaluation shows that state-of-the-art BERT-GPT performs better. [ABSTRACT FROM AUTHOR]

Hotels are the places that people choose to carry out activities such as recreation, business, and others. Guests expect to get good service, get comfort while staying at the hotel. During this pandemic, the hotel has started to enforce strict health protocols by reducing the number of employees working, by reducing the number of workers expected to minimize transmission in the hotel environment. With the reduction in hotel employees, it creates a shortage of labor in serving hotel guests who arrive. For this purpose, we created a chatbot, called as e-concierge, that can provide information about the hotel to the guests. The chatbot is also expected to help push the hotel industry forward by combining technology. The chatbot is developed using the AI-based Dialoglfow application that can answer questions asked by staying guests. Dialogflow uses json to be able to reply to messages with the design we want and uses node.js. Based on our evaluation, the chatbot can employ the purpose as e-concierge which can replace customer service in the hotel. [ABSTRACT FROM AUTHOR]

Due to the coronavirus pandemic international conflicts, dramatic changes of daily living have been enforced, including new ways of providing patient assistance, based on artificial intelligence. The influence of these changes on people's mental health is still insufficiently analyzed and explored. Chatbots like Woebot, Wysa and Tess are gaining popularity, being attractive and easy to use. These achievements led us to develop a new application, being still in the testing phase, which has a positive impact on mental healthcare issues. It is a conversational system capable to diagnose people's negative, depressive, and anxious emotions during chatting, and to act as a psychological therapist and virtual friend. The proposed system, throughout the conversation, succeeds to decrease the patient's insecurity sentiments, by comforting their mood. In fact, an intelligent assistant for different mental health issues like stress, anxiety and depression, could become a very helpful information system. [ABSTRACT FROM AUTHOR]

Today's competitive world uses different marketing opportunities to achieve business goals. Customer experience is a core component in marketing studies; firms need to create strong and enduring customer experiences. To achieve this goal, enterprises can use technology, especially since it reshapes the nature of service, customers' experiences, and customer relationship management. In this sense, the purpose of the present article is to highlight the role of AI throughout chatbot in enhancing customer experience. We try to bring some answers to our following problematic: how do AI based Chatbots influence the customer experience? To do so, we conducted a systematic literature review. 23 marketing journals were reviewed from two prominent databases (Elsevier and Web of Science). Finally, Fourteen peer-reviewed journal publications in marketing field were analysed. The study found that the analysed marketing journals paid less attention to intelligent agents within the field of customer experience. Another observation is that most of research on chatbots and customer experience in these two databases were conducted between 2020 and 2021. Research implications and directions for future research across marketing field were suggested. [ABSTRACT FROM AUTHOR]

Chatbots are increasingly finding their way into e-commerce and e-services, as their implementation opens up promising opportunities to improve customer service. The present paper examines chatbots in this context, elaborating on their functional aspects that are rapidly leading to significant improvements in service quality. First, based on a literature review of recent publications in this field, an overview of their key features and functionalities underlining the relevance of chatbots for customer service is provided. Second, a further contribution is made by introducing two categories of chatbots' objectives based on their functional dedication, i.e. "improvement of service performance" and "fulfillment of customer's expectations". The considered chatbots' customer-related functions are interaction, entertainment, problem-solving, trendiness, and customization. The chatbot categories are discussed in detail. Their positive influence on service quality, constituting the chatbots' functional goal, as well as the potential of chatbots in customer service are pointed out. [ABSTRACT FROM AUTHOR]

Conversational Agents are widely used in different domains to automate tasks and help to improve user experience. In recent decades, AI systems, thanks to deep learning methods and Natural Language Processing (NLP) approaches, can interact with users, understand their needs, map their preferences and recommend an appropriate action with no human intervention. However, chatbots in the education field have received limited attention. In this work, we use Xatkit, a chatbot development framework, for the definition of our Chatbot and propose an Encoder-Decoder framework for intent recognition. For the encoder, we encode utterances as context representations using bidirectional transformer (CamemBERT). For the decoder, we use an intent classification decoder to detect the student's intent. Our chatbot will be tested in the field of education to improve and simplify teaching for professors and learning for students as well as reducing faculty burnout and raising the speed of comprehension. [ABSTRACT FROM AUTHOR]

Designing user interfaces requires the efficient management of elements that interact with the user and attract their attention. In the development of technologies supporting the development of chatbots, few studies have focused on the visual aspects of the interface. Changes in the chatbot area can be of different natures, such as increasing or decreasing the number of messages. Due to habituation (change blindness), messages delivered by chatbots may not be noticed. The main goal of the present study was to examine the impact of changes within the chatbot on user behaviour and the possibility of directing user attention to the chatbot area. This study showed that the intensity and types of changes within the chatbot can improve performance and successful message delivery to users. [ABSTRACT FROM AUTHOR]

Intelligent technologies are widely implemented in different areas of modern society but specific approaches should be applied in services. Basic relationships refer to supporting customers and people responsible for services offering for these customers. The aim of the paper is to analyze and evaluate the state-of-the art of artificial intelligence (AI) applications in the hospitality industry. Our findings show that the major deployments concern in-person customer services, chatbots and messaging tools, business intelligence tools powered by machine learning, and virtual reality & augmented reality. Moreover, we performed a survey (n = 178), asking respondents about their perceptions and attitudes toward AI, including its implementation within a hotel space. The paper attempts to discuss how the hotel industry can be motivated by potential customers to apply selected AI solutions. In our opinion, these results provide useful insights for understanding the phenomenon under investigation. Nevertheless, since the results are not conclusive, more research is still needed on this topic. Future studies may concern both qualitative and quantitative methods, devoted to developing models that: a) quantify the potential benefits and risks of AI implementations, b) determine and evaluate the factors affecting the AI adoption by the customers, and c) measure the user (guest) experience of the hotel services, fueled by AI-based technologies. [ABSTRACT FROM AUTHOR]

Over the past few years, there has been a boost in the use of commercial virtual assistants. Obviously, these proprietary tools are well-performing, however the functionality they offer is limited, users are "vendor-locked", while possible user privacy issues rise. In this paper we argue that low-cost, open hardware solutions may also perform well, given the proper setup. Specifically, we perform an initial assessment of a low-cost virtual agent employing the Rasa framework integrated into a Raspberry Pi 4. We set up three different architectures, discuss their capabilities and limitations and evaluate the dialogue system against three axes: assistant comprehension, task success and assistant usability. Our experiments show that our low-cost virtual assistant performs in a satisfactory manner, even when a small-sized training dataset is used. [ABSTRACT FROM AUTHOR]

A Chatbot is a conversational agent that simulate human conversation, through text or voice messages. One of the first goals of a Chatbot is to interact with the user just like a human. When it comes to Health Chatbots, another main goal is to be able to get the correct answer to the user request. In this paper we propose a general Architecture of an AI-Powered Health Chatbot with Four components to reach the two goals, which integrates dialogue and communication part in natural language understanding (NLU) and natural language generation (NLG), and the expert part based on deep learning whose function is to give appropriate response from pre-formatted data. [ABSTRACT FROM AUTHOR]

Chatbots are currently used in various online applications, most of the case for shopping or as a personal assistant. These chatbots offer a range of potential benefits, including personalization and 24/7 instant availability. These positive aspects of chatbots can be beneficial in the educational sector. They represent a new type of human-machine interface in natural language. However, chatbots in academia have received only limited attention, for example by providing organizational support for studies or courses and exams. This branch of research is just emerging in the scientific community, therefore, in our article, we set up a chatbot in the field of educational and professional guidance which is based on the theory of John Holland and the RIASEC questionnaire in order to determine the dominant type of personality of undergraduate and graduate students that wants to enter the job market. [ABSTRACT FROM AUTHOR]

The creation and training of a smart conversational agent has long been a dream of the human race and a huge challenge for scientists and programmers. Until recently, it was still just a dream. However, state-of-the-art technologies, like deep learning and neural networks, give language teachers a new hope, providing them with smart chatbots able to learn through communication just like humans. Today, the availability of chatbots helps to create a new educational scenario for foreign language learners. It suits well their fast-paced lives, allowing multitasking and making the work of ESL educators a lot easier and a way more effective. In that way chatbots could represent one of the basic components of microlearning. [ABSTRACT FROM AUTHOR]

The main purpose of this article is to describe how to use chat bots in learning management systems. The substantiation of the importance of using chat bots, as well as the tasks that they can solve in the learning process. The classification of bots is given depending on the types of tasks they perform and their place in educational processes. In addition, methods and approaches to training chat bots operating in LMS are described. [ABSTRACT FROM AUTHOR]

Technology is increasingly becoming a massive part of today's healthcare scenario. Technology has changed the way how patients communicate with doctors and not only that, but also how healthcare is administered. Artificial intelligence and Chabots are two groundbreaking technologies that have changed how patients and doctors perceive healthcare. To make healthcare system more interactive a diagnostic Chabot is designed and developed using latest algorithms in machine learning, decision tree algorithm to help the user to form a diagnosis of their condition based on their symptoms. The system will be fed with information pertaining to various diseases and using NLP, it will be able to understand the user query and give a suitable response. The system can be used for effective information retrieval in a similar manner like siri, alexa etc but the scope will be limited to disease diagnosis. [ABSTRACT FROM AUTHOR]

PT Kreatif Dinamika Integrasi will develop a chatbot as the computer program designed to simulate intellectual conversation via text and voice by using Artificial Intelligence (AI). However, because development costs are high enough, it is necessary to gather opinions on the community's enthusiasm that will support the decision whether the development should or should not to have proceeded. Community sentiment analysis of data obtained from social media Twitter. Appraisal Theory method is exercised utilizing the R Studio tool to perform tweet crawling, preprocessing, scoring and term weighting. R is an open-source language and environment used for statistical computing and graphics. The results of the analysis indicate positive sentiment where the positive and negative comparison ratio was 4,78. The expression of sentiment analysis results by using the NRC library is 547 for "anticipation" sentiment and 728 for "trust" expression so that the technology of chatbot can be developed by the company. Although the results of the analysis of obtained are positive assessment, there is still the negative sentiment in the community, so it is necessary to act to reduce the risk. [ABSTRACT FROM AUTHOR]

Chatbot program has been empirically proven help to improve the engagement with users. Moreover, the implementation of a chat-bot program in the industry helps the company to reduce their operational costs in engaging with their customers and employees. There are still quite a number of problems existed in order to build a human-like chatbot program. Understanding a natural conversation and replying back to the conversation the interlocutors, keeping the conversation flowing naturally is a cumbersome task for a computer. This research aims to design an emotionally realistic chatbot system to enhance the believability of the chatbot using Artificial Intelligence Markup Language (AIML) and Information State. The results show that there is a statistically significant improvement to the chatbot believability in the system that has emotions variables induced compare to the one without emotions. Moreover, 63,33% of the respondents perceived Aero and Iris as two different individuals. The future work of this research is to deploy and have an exploration of the chatbot system to other cases. [ABSTRACT FROM AUTHOR]

Question and Answering (QA) system is a problem in natural language processing that can be used as the system of dialogs and chatbots. It can be used as a customer service that can provide a response to the customer quickly. A QA system receives an input in the form of sentences and produces the predictive sentences that are responses to the input. Therefore, a model that can learn such conversations is needed. This research focuses on developing a chatbot based on a sequence-to-sequence model. It is trained using a data set of conversation from a university admission. Evaluation on a small dataset obtained from the Telkom University admission on Whatsapp instant messaging application shows that the model produces a quite high BLEU score of 41.04. An attention mechanism technique using the reversed sentences improves the model to gives a higher BLEU up to 44.68. [ABSTRACT FROM AUTHOR]

Many companies want or prefer to use chatbot systems to provide smart assistants for accompanying human specialists especially newbies with automatic consulting. Implementation of a really useful smart assistant for a specific domain requires a knowledge base for this domain, that often exists only in the form of text documentation and manuals. Lacks of properly built datasets and often expensiveness in resources and time to build one from scratch to apply data-driven methods with high quality. It motivates to seek a solution that can work without such data or require only a small amount of it though having reduced quality. The reformulation of the task into an information retrieval problem where the assistant responds with a piece of documentation instead of generated sentences may make the task easier but doesn't solve the whole problem. It allows using of metrics-based methods with reduced search quality or data-driven methods which also needs a great amount of data. In this paper, we propose a new ensemble-based data-driven method that tries to learn a scoring function by combining independent functions from a predefined set. The method may substantially improve the quality of the search in comparison with pure metrics-based methods while requiring significantly less data for training than data-driven methods. [ABSTRACT FROM AUTHOR]

Free will is an important component of consciousness. Modeling an artificial consciousness requires clarifying the significance and the definition of free will. This study proposes a definition of free will similar to the epsilon-delta definition of continuous space (e.g., real numbers). Selection capability and frame expanding potential (i.e., the ability to allow for the exploration of further options), which are significant functions of free will, are discussed in the problem-solving context. We also propose a Turing test with multiple agents in which the intelligence of humans and machines will be relatively scored based on chats in a mixed community of humans and machines. Agents (machines) fail in the multiple agents Turing test because they lack the ability to evaluate chats with another agent, as well as chats between two other agents. [ABSTRACT FROM AUTHOR]