Over the last ten years there has been a growing interest around text-based chatbots, software applications interacting with humans using natural written language. However, despite the enthusiastic market predictions, ‘conversing’ with this kind of agents seems to raise issues that go beyond their current technological limitations, directly involving the human side of interaction. By adopting a Human-Computer Interaction (HCI) lens, in this article we present a systematic literature review of 83 papers that focus on how users interact with text-based chatbots. We map the relevant themes that are recurrent in the last ten years of research, describing how people experience the chatbot in terms of satisfaction, engagement, and trust, whether and why they accept and use this technology, how they are emotionally involved, what kinds of downsides can be observed in human-chatbot conversations, and how the chatbot is perceived in terms of its humanness. On the basis of these findings, we highlight open issues in current research and propose a number of research opportunities that could be tackled in future years.

The human side of human-chatbot interaction: A systematic literature review of ten years of research on text-based chatbots

The introduction of Artificial Intelligence technology enables the integration of Chatbot systems into various aspects of education. This technology is increasingly being used for educational purposes. Chatbot technology has the potential to provide quick and personalised services to everyone in the sector, including institutional employees and students. This paper presents a systematic review of previous studies on the use of Chatbots in education. A systematic review approach was used to analyse 53 articles from recognised digital databases. The review results provide a comprehensive understanding of prior research related to the use of Chatbots in education, including information on existing studies, benefits, and challenges, as well as future research areas on the implementation of Chatbot technology in the field of education. The implications of the findings were discussed, and suggestions were made.

Chatbots applications in education: A systematic review

Exploring the role of personality, trust, and privacy in customer experience performance during voice shopping: Evidence from SEM and fuzzy set qualitative comparative analysis

Artificial intelligence applications in supply chain management

Internet of Things (IoT) based voice interaction system, as a new artificial intelligence application, provides a new human–computer interaction mode. The more intelligent and efficient communication approach poses greater challenges to the semantic understanding module in the system. Facing with the complex and diverse interactive scenarios in practical applications, the academia and the industry urgently need more powerful Natural Language Understanding (NLU) methods as support. Intent Detection and Slot Filling joint task, as one of the core sub-tasks in NLU, has been widely used in different human–computer interaction scenarios. In the current era of deep learning, the joint task of Intent Detection and Slot Filling has also changed from previous rule-based methods to deep learning-based methods. It is an important problem to explore how to realize the models of these tasks to be refined and targeted designed, and to make the Intent Detection task better serve the improvement of precision of Slot Filling task by connecting the before and after tasks. It has great significance for building a more humanized IoT voice interaction system. In this study, we designed two joint models to realize Intent Detection and Slot Filling joint task. For the Intent Detection type task, one is based on BiGRU-Att-CapsuleNet (hybrid-based model) and the other is based on the RCNN model. Both methods use the BiGRU-CRF model for the Slot Filling type task. The hybrid-based model can enhance the semantic capture capability of a single model. And by combining specialized models built independently for each task to achieve a complete joint task, it can be better to achieve optimal performance on each task. This study also carried out detailed comparative experiments of tasks and joint tasks on multiple datasets. Experiments show that the joint models have achieved competitive results in 7 typical datasets included in multiple scenarios in English and Chinese compared with other models.

Natural language understanding approaches based on joint task of intent detection and slot filling for IoT voice interaction

Natural Language Interfaces allow human-computer interaction through the translation of human intention into devices’ control commands, analyzing the user’s speech or gestures. This novel interaction mode arises from advancements of artificial intelligence, expert systems, speech recognition, semantic web, dialog systems, and natural language processing, bringing the concept of Intelligent Personal Assistant (IPA). There is currently a vast literature on this subject. However, in the best of our knowledge, there is no thorough analysis of the state-of-the-art in the field. In this context, we present in this article a survey of the field, discussing the main trends, critical areas, and challenges of an IPA. Another contribution is the proposition of a taxonomy for IPA classification. The method used to achieve these objectives consisted of a systematic literature review based on the population, intervention, comparison, outcome, and context (PICOC) criteria. As a result, we started from more than 3472 scientific articles published in the last six years, searched on a set of databases chosen to increase the probability of finding highly relevant articles. The review selected the 58 most significant articles, identifying challenges and open questions. We also discuss in the article the current status, usage, security and privacy issues, types, and architectures regarding an IPA. We conclude that usability, security, and privacy directly affect the confidence of the user in adopting an IPA.

Intelligent personal assistants: A systematic literature review

Frauds on the purchasing area impacts companies all around the globe. One of the possibilities to tackle this issue is through the usage of audits, however, due to the massive volume of the data available today, it is becoming impossible to manually check all the transactions of a company, hence only a small sample of the data is verified. This work presents a new approach through the usage of signature detection with clustering techniques to increase the probability of inclusion of fraud-related documents in sample sets of transactions to be audited. Due to a non-existence of a public database related to the purchase area of companies for fraud detection, this work uses real procurement data to compare the probability of selecting a fraudulent document into a data sample via random sampling versus the proposed model as well as exploring what would be the best clustering algorithm for this specific problem. The proposed model improves the current state-of-the-art since it does not require pre-classified datasets to work, is capable of operating with a very high number of data records and does not need manual intervention. Preliminary results show that the probability of including a fraudulent document on the sample via the proposed model is approximately seven times higher than random sampling.

A Hybrid Model for Fraud Detection on Purchase Orders

Previous work on textual entailment has not fully exploited aspects of deep linguistic relations, which have been shown as containing important information for entailment identification. In this study, we present a new method to compute semantic textual similarity between two sentences. Our proposal relies on the integration of a set of deep linguistic relations, lexical aspects and distributed representational resources. We used our method with a large set of annotated data available from the ASSIN Workshop in the PROPOR 2016 event. The achieved results score among the best-known results in the literature. A perceived advantage of our approach is the ability to generate good results even with a small corpus on training tasks.

Enhancing Brazilian Portuguese Textual Entailment Recognition with a Hybrid Approach

Identify and classify attacks through Intrusion Detection Systems is one constant challenge for security professionals. Computer networks are one of the significant IT components that support classification operations. Machine Learning (ML) techniques can aid in this process by providing methods capable of making decisions based on previously known information. In light of this, literature shows that Quadratic Discriminant Analysis (QDA) is barely explored as a classification method for IDS. To fill this gap, this study aims to create a new classifier able to distinguish legitimate network traffic from an attack by adopting ML techniques and QDA algorithms for identifying Port Scan and DoS Slowloris attacks.

Allan de Barcelos Silva

Papers

Intelligent personal assistants: A systematic literature review

A Hybrid Model for Fraud Detection on Purchase Orders

Enhancing Brazilian Portuguese Textual Entailment Recognition with a Hybrid Approach

Using Quadratic Discriminant Analysis by Intrusion Detection Systems for Port Scan and Slowloris Attack Classification

Wearable Health Care Ubiquitous System for Stroke Monitoring and Alert