Figure 2 - uploaded by F. Colace
Content may be subject to copyright.
Source publication
Technological progress seems unstoppable: large companies are ready to implement more and more
sophisticate solution to improve their productivity. The near future may be represented by so-called Chatbot,
already present in the instant messaging platforms and destined to become more and more popular. This paper
presents the realization of a prototy...
Similar publications
In this work-in-progress paper we discuss the challenges in identifying effective and scalable crowd-based strategies for designing content, conversation logic, and meaningful metrics for a reminiscence chatbot targeted at older adults. We formalize the problem and outline the main research questions that drive the research agenda in chatbot design...
Chatbot is widely popular now-a-days and catching speed as an application of computer communication. Some programs respond intelligently like human. This type of program is called a Chatbot. This paper addresses the design and implementation of a Chatbot system. We will also study another application where Chatbots could be useful and techniques us...
Background:
A chatbot is a software that interacts with users by simulating a human conversation through text or voice via smartphones or computers. It could be a solution to follow up with patients during their disease while saving time for health care providers.
Objective:
The aim of this study was to evaluate one year of conversations between...
Current neural-network based conversational
models lack diversity and generate boring responses
to open-ended utterances. Priors such
as persona, emotion, or topic provide additional
information to dialog models to aid response
generation, but annotating a dataset
with priors is expensive and such annotations
are rarely available. While previous me...
Citations
... However, many users remain reluctant to interact with chatbots indicating, for example, a lack of empathy and/or personal emotion [12]. Furthermore, other issues including personal privacy (Song et al., 2022), feelings of discomfort [51], and difficulty in "real" interaction [17] can directly lead to the poor user experience. Therefore, how to provide more humanizing services, safe and reliable interactive environment, and better user experience are the challenges encountered by chatbots today. ...
Since chatbots have been integrated into people’s lives from various industries, human-chatbot interaction has begun to attract widespread attention in academia. Still, contributions to the systematic mapping of this field are lacking. This paper is the first to present a systematic review of human-chatbot interaction research using bibliometric analysis. A total of 3013 publications (from the year 2000 to 2022) from Web of Science database were analysed to uncover the current status and research trend in human-chatbot interaction domain. The analysis focused on temporal and geographical distribution of these publications and identified the most influential publication outlets, institutes, articles, and authors. Additionally, keyword co-occurrence analysis and temporal distribution of keywords showed that primary topics in human-chatbot interaction mainly concentrate on techniques and methods in chatbot systems design, extensive applications in various fields, user experience and emotional expression, humanizing features design, and perceived privacy risk and ethics. Finally, this paper sheds light on a comprehensive understanding of human-chatbot interaction research and provides directions for future research in this field.
... After that, an ontology of learning ideas is generated by course, lesson, subject, or user. Petri net-based ChatBots for type recommendation have been researched [13]. It creates a type of ontology. ...
Conversational agents like Alexa from Amazon, Siri from Apple, Assistant from Google, and Cortana from Microsoft demonstrate extraordinary research and potential in conversational agents. A conversational agent, chatter-bot, or chatbot is a piece of computer software supposed to communicate at a level of intelligence comparable to a person's. Chatbots are designed for various purposes, such as task-oriented helpers and creators of open-ended discourse. Numerous approaches have been studied, from primitive types of hard-coded response generators to contemporary ways of constructing artificial intelligence. These are classified as rule-based or neural network-based systems. Unlike the rule-based technique, which is based on pre-defined templates and responses, the neural network approach is based on deep learning models. Rule-based communication is optimal for more straightforward, task-oriented conversations. Open-domain conversational modeling is a more complicated topic that depends heavily on neural network techniques. This article begins with an overview of chatbots before diving into the specifics of a variety of traditional, rule-based, and neural network-based methods. A table summarising previous field research closes the survey. It looks at the most recent and vital research on the subject, the evaluation instruments used areas for improvement, and the applicability of the proposed methods.
... Several researchers developed chatbots for recommender systems. Colace et al. [5] developed a chatbot system using Petri Net to recommend vehicle tires. The research got the results of giving correct recommendations by 65.32%, giving correct recommendations but not in accordance with user needs by 13.87%, and giving wrong recommendations by 20.81%. ...
p> Currently, the online movie streaming business is growing rapidly, such as Netflix, Disney+, Amazon Prime Video, HBO, and Apple TV. The recommender system helps customers in getting information about movies that are in accordance with their wishes. Meanwhile, the development of messaging platform technology has made it easier for many people to communicate instantly. Utilizing a messaging platform to build a recommender system for movies, provides special benefits because people often access the messaging platform all the time. In the Indonesian language, there are many slang terms that the system must recognize. In this study, we build a chatbot on a messaging platform which users can interact with the system in natural language (in Indonesian language) and get recommendations. We use rule-based and maximum likelihood as a method in natural language processing (NLP), and content-based filtering for the recommendation process. The recommender system interaction is built through a conversation mechanism that will form a conversational recommender system. The interaction is based on a chatbot which is built using Dialogflow and implemented on the telegram. We use the accuracy of recommendations and user satisfaction to evaluate the system performance. The results obtained from the user study indicate that the NLP approach provides a positive experience for users. In addition, the system also produces an accuracy value of 83%. </p
... Although consumers are generally likely to use a chatbot for their travel planning, satisfaction with this service may affect usage (Pillai & Sivathanu, 2020). Some authors report privacy issues (Pagallo, 2013;Zamora, 2017), difficulty in obtaining information (Colace et al., 2017), and feelings of discomfort (Luo et al., 2019) in using chatbots. Emerging research shows the diverse contexts of chatbot applications. ...
Several industries recognize the potential of Artificial Intelligence to complete tasks. However, there is limited research on chatbots, and a gap in the research on what factors contribute to consumers' intention to continue using them. This research aims to analyze the relationship of the TAM and ISS dimensions, continuing to use satisfaction and brand attachment as mediators, and using the need for interaction with the employee as a moderating dimension. The results indicated that the role of brand attachment increases the model's explanatory power, and the need for interaction with the employee positively favors the relationship between brand attachment and satisfaction.
... In addition, since human experiences are generated through their activities, some studies have proposed a system that is capable of framing repetitive everyday human activities to provide a mechanism of dynamic and automatic invocation of services considering the context through the context dimension tree [54], whereby context is described as any information that can be used to characterise the structure of an entity by developing a system which is context aware, to provide relevant information and/or services to the user [54]. Hence, to improve workflow management, a system capable of extrapolating certain keywords from text online or through an ontology of reference allows one to achieve knowledge and links between concepts using a selected model such as Petri-Nets, which lends well for online-based application [20,55]. The Chatbot furnishes such functions, as it can provide suggestions to humans when filling web-based applications, but because human interactions are unpredictable, it can prove difficult to accurately predict the knowledge base library and ontology of references that can feed such KMS [20]. ...
... Hence, to improve workflow management, a system capable of extrapolating certain keywords from text online or through an ontology of reference allows one to achieve knowledge and links between concepts using a selected model such as Petri-Nets, which lends well for online-based application [20,55]. The Chatbot furnishes such functions, as it can provide suggestions to humans when filling web-based applications, but because human interactions are unpredictable, it can prove difficult to accurately predict the knowledge base library and ontology of references that can feed such KMS [20]. ...
The expectations of organizations within industries that perform MoOSTs when adopting knowledge management (KM) as part of their organizational process are to improve the ability to execute their core business functions in the process of capturing as well as retaining expert knowledge. However, existing literature is limited in MoOSTs-specific knowledge management systems (KMS) that can assist with experience capturing, collation and transfer. This is partly due to the challenges associated with the ability to design, implement and test the efficacy of such KMS in practice, owing to many intricately identified knowledge barriers within MoOSTs. In this study, through a cement manufacturing process case study, a proposal depicting a typical KM process within MoOSTs is presented along with an early stage interactive web-based KMS for MoOSTs. The developed KMS is termed MoOSTs knowledge platform (MoOSTsKP). The MoOSTsKP was evaluated by experts for its fluidity, resilience, and adaptability to different MoOSTs organizations, which are crucial elements for integration into existing MoOSTs information technology (IT) systems. The MoOSTsKP is identified with having many benefits including prioritization of MoOSTs activities based on an in-built criticality assessment model, which enables MoOSTs experts to instantly identify priority knowledge classes and in turn rationalise the workload associated with knowledge capture and reuse. Based on expert opinions, it is envisaged that the proposed MoOSTsKP would contribute immensely towards the alleviation of challenges associated with incessant loss of vital expertise.
... According to the building of PDTs using a set of collaborating twins, each DT relation to other DTs is defined and stored in the knowledgebase, such as instanceinstance relations, inheritance, parent-child relations, and the whole system to remain consistent. Then, the knowledgebase contains the set of knowledge rules and ontologies learned through relevant ML techniques from DT-based historical data [44]. Furthermore, knowledge rules are used to refine the knowledgebase by identifying new conditions using rule-based analysis. ...
Digital twins (DTs) play a vital role in revolutionising the healthcare industry, leading to more personalised, intelligent, and proactive healthcare. With the evolution of personalised healthcare, there is a significant need to represent a virtual replica for individuals to provide the right type of care in the right way and at the right time. Therefore, in this paper, we surveyed the concept of a personal digital twin (PDT) as an enhanced version of the DT with actionable insight capabilities. In particular, PDT can bring value to patients by enabling more accurate decision making and proper treatment selection and optimisation. Then, we explored the progression of PDT as a revolutionary technology in healthcare research and industry. However, although several research works have been performed for smart healthcare using DT, PDT is still at an early stage. Consequently, we believe that this work can be a step towards smart personalised healthcare industry by guiding the design of industrial personalised healthcare systems. Accordingly, we introduced a reference framework that empowers smart personalised healthcare using PDTs by bringing together existing advanced technologies (i.e., DT, blockchain, and AI). Then, we described some selected use cases, including the mitigation of COVID-19 contagion, COVID-19 survivor follow-up care, personalised COVID-19 medicine, personalised osteoporosis prevention, personalised cancer survivor follow-up care, and personalised nutrition. Finally, we identified further challenges to pave the PDT paradigm toward the smart personalised healthcare industry.
... Among the other application domains, electronics (e.g., digital cameras), fashion, general e-commerce and health & food recommendations received some attention worth mentioning, e.g., Angara et al. (2017), Zeng et al. (2018), Yu et al. (2019a), Shimazu (2002). Research on other domains is, however, very sparse, including a number of application cases which were only addressed in one single paper, e.g., the recommendation of podcasts, scientific papers or car tires (Yang et al. 2018;Colace et al. 2017;Loh et al. 2010). ...
Conversational recommender systems aim to interactively support online users in their information search and decision-making processes in an intuitive way. With the latest advances in voice-controlled devices, natural language processing, and AI in general, such systems received increased attention in recent years. Technically, conversational recommenders are usually complex multi-component applications and often consist of multiple machine learning models and a natural language user interface. Evaluating such a complex system in a holistic way can therefore be challenging, as it requires (i) the assessment of the quality of the different learning components, and (ii) the quality perception of the system as a whole by users. Thus, a mixed methods approach is often required, which may combine objective (computational) and subjective (perception-oriented) evaluation techniques. In this paper, we review common evaluation approaches for conversational recommender systems, identify possible limitations, and outline future directions towards more holistic evaluation practices.
... In the automotive domain, a software module prototype of a conversational workflow for a Chatbot has been constructed and modeled with Petri nets that can communicate and propose the most suitable tires for users (Colace et al. 2017). A multi-agent orchestration framework for task automation is presented by Rizk et al. (Rizk et al. 2020b). ...
... BPMN is used as a standard for process modeling, parsing, and execution. One of the main components of the proposed system is the process engine, and similar concepts are mentioned here, where it is called the Workflow Manager (Colace et al. 2017) and here, where it is called the Orchestrator . Although they are used as the chatbot state management modules, the same can be said for our process engine, which is, in a way, a chatbot state orchestrator or socalled manager. ...
A successful business operates on many interacting processes to meet the business goals; thus, organizing these processes in a structured business model is essential. Business process modeling notation (BPMN) is a widely used business modeling technique based on simple business and logic specifications understandable not only by domain experts but also to the broader audience. Although it provides support for the process execution, many BPMN models serve only for documentation purposes. This paper positions the lack of coordination between the process execution and the frontend interface as drivers of slow BPMN adoption. To close the gap between execution and interface, we present a system architecture that provides external task automation and interactive human task completion using a chatbot structure powered by natural language processing (NLP) and BPMN. We have evaluated the performance of the proposed architecture on the process of internship applications for the Faculty of Informatics in Pula, Croatia.
... ). Other issues related to privacy apprehension(Zamora 2017), dissatisfaction feelings(Luo et al. 2019) and interaction difficulties(Colace et al. 2017) may arise. Thus technology sometimes cannot serve customers without human intervention, so (Nguyen 2019) a human can cope better with situations and subjects than a chatbot, especially in complex situations. ...
With the proliferation of the use of chatbots across industries, business-to-business (B2B) businesses have started using cognitive chatbots for improved customer service which signifies our research. By extending the Technology Acceptance Model and Information Systems Success Model, this study examines personalised contextual customer service using cognitive chatbot. A quantitative research method is applied to the primary data collected from 300 respondents of B2B businesses. The study contributes to the limited research on chatbots and suggests improvement in customer service. The findings provide evidence of high value by customers, particularly while checking for real-time information on reliability and accessibility of products/services. The automated answers to repetitive questions on the recurrent issues create a seamless experience for the customers. This research makes significant theoretical contributions by integrating two models into a simplified model in chatbot literature and manifest that trust affects the willingness to use the cognitive chatbot which drives automation.
... Generally, applications are built from the various ways of using location data. The applications for indoor localization concern various fields, such as industrial (localization of products, equipment) [32], logistics (localization of goods, pallets, forklifts, trans pallets, and inventory in real time) [33], access control (localization of people and access permits) [34], health and assistance (localization of medical equipment, health workers, patients) [35], sports (tracking the movements and trajectories of athletes) and many others [36]. It is possible to foresee many of their applications in context aware computing, especially as regards recommender systems [37] in the automotive field for the localization and analysis of data in tunnels and places, where the GPS signal is not present [38]. ...
In recent years, a great number of applications in Internet of Things (IoT) have been developed. In this context, many methodologies and technologies are used for several frameworks, including indoor localization. In this field, as highlighted in recent years, one of the most important aims of modern indoor applications in IoT is to identify how to manage and correctly convey people flow. This study aims to investigate the most common methods, technologies and applications for indoor localization in IoT and analyze the major systems currently in use and the application of these solutions to actual conditions. Following this, we propose an innovative method to detect people flow in indoor location. Based on Bluetooth low energy (BLE) technology, in this paper we analyze the possibility to use our system for many kinds of applications. The first experimental results show good performance of our system.
