Chatbots are artificial intelligence tools that interact with people in different contexts. A chatbot can be useful to streamline daily processes, serve customers 24 hours a day, provide information about classes, among other things. The appearance of new development technologies has made creating a chatbot an increasingly fast and straightforward process, bringing this kind of applications to people who had never considered using them before. However, this speed in development can lead to specific problems, many of them caused by the lack of usability evaluations. Heuristic usability evaluations are user interface review processes carried out by experts and are an essential part of any assessment process. To date, there are no heuristics to evaluate the usability of chatbots. Therefore, this work proposes five usability heuristics in chatbots that come from the experience developing this type of applications, as well as from a broad review of state of the art. The set of heuristics was tested using a case study with the help of five experts, who evaluated an education-oriented chatbot. The results revealed that, although the proposed heuristics need refinement, they are an excellent first step in broadening the horizon of usability evaluations in chatbots.

Online social networks provide technological support for making up virtual groups of any size, whose members share common interests and interact through the Internet. A person joins a social network not only owing to its popularity and the quality of its contents, but also thanks to the User Experience (UX) that the platform offers. A crucial factor in the growth and survival of any virtual social group is participation, which should be facilitated by suitable user tools supplied by the platform. However, this is not always the case. Anticipated User eXperience (AUX) allows knowing the idealisations, hopes, and desires of the users in a very early stage of any development. In this paper, we propose an AUX and UX evaluation method for user tools of social networks, whose goal is to improve their design, and through it, the participation of people. We tested our method by an experimental design that included the construction of paper prototypes and execution of tasks in actual platforms. The AUX and UX of the participants were measured with AttrakDiff. As shown by our results, based on their previous experience, participants have fixed ideas on the behaviour of user tools, having a visible impact when their expectations are not met.

Chatbots, text or voice software entities, are consolidating their position in the education sector, as they have gone from being rustic tools to systems that can take an active role in the teaching and learning process. That is why we decide to elaborate a Systematic Mapping Study of works that have been published on educational chatbots in the last years. Our analysis has four objectives: 1) to know the purpose of chatbots; 2) to identify the educational levels in which the chatbots are employed; 3) to examine which interaction mechanisms are implemented by chatbots; and 4) to explore which technologies and software architectures predominate in the development of educational chatbots. Following solid methodologies for systematic reviews, we compiled 104 papers. Through the analysis of these works, we obtained an overview that can be useful for both specialists and newcomers to the domain, as it helps them understand the existing trends in these applications. Additionally, the discussion extends into the disruptive impact of generative AI and outlines critical open research questions that guide future investigations in educational chatbot development.

Social networks are a meeting point on the Internet; people use them to exchange opinions, help each other, or have fun. The growth and success of a social network are multifactorial phenomena but can be generalised into two factors: the quality of the content, and the User eXperience (UX) that the platform offers. Thus, the design of the GUI of a social network must come from the needs of its users. It is necessary to study the UX over time, before and after the development of the platform. Before, the Anticipated User eXperience (AUX) allows knowing the idealisations and desires of users. After, the UX is the measure of the actual system. We propose a UX over time evaluation method for user tools in social networks to have a way to contrast both results, improve the design of user tools, and finally increase participation. To test our evaluation method, we designed an experiment in which users had to devise on paper different user tools. Then, they had to evaluate similar elements but this time in actual social networks. The AUX and UX of the participants were measured with AttrakDiff. Our results show that, based on their previous experience, participants had established ideas on the behaviour of user tools, having a visible impact when their expectations were not met.