Hey Siri, What Can I Tell About Sancho Panza in My Presentation? Investigating Siri as a Virtual Assistant in a Learning Context? (original) (raw)
Related papers
Proceedings of the 53rd Hawaii International Conference on System Sciences, 2020
Conversational agents such as Apple's Siri or Amazon's Alexa are becoming more and more prevalent. Almost every smart device comes equipped with such an agent. While on the one hand they can make menial everyday tasks a lot easier for people, there are also more sophisticated use cases in which conversational agents can be helpful. One of these use cases is tutoring in higher education. Several systems to support both formal and informal learning have been developed. There have been many studies about single characteristics of pedagogical conversational agents and how these influence learning outcomes. But what is still missing, is an overview and guideline for atomic design decisions that need to be taken into account when creating such a system. Based on a review of articles on pedagogical conversational agents, this paper provides an extension of existing classifications of characteristics as to include more fine-grained design aspects.
Embodied conversational agents in Computer Assisted Language Learning
This paper describes two systems using embodied conversational agents (ECAs) for language learning. The first system, called Ville, is a virtual language teacher for vocabulary and pronunciation training. The second system, a dialogue system called DEAL, is a role-playing game for practicing conversational skills. Whereas DEAL acts as a conversational partner with the objective of creating and keeping an interesting dialogue, Ville takes the role of a teacher who guides, encourages and gives feedback to the students.
Interactive Competence in Student Use of a Conversational Agent
2013
In the past several years, there has been debate among Computer Assisted Language Learning (CALL) researchers regarding the usefulness of conversational agents (chatbots) as language learning tools. Some researchers highlight their potential to provide practice in the target language, while others decry the shortcomings of the technology. This exploratory study investigates the features of student text conversations with a chatbot-based virtual agent. Conversation transcripts from an entire school year of use were coded, analyzed, and compared to current ACTFL proficiency guidelines. Results showed that students often demonstrated degrees of linguistic competence which allowed them to engage in relatively cohesive interactions with the conversational agent.
Tutor design for speech-based interfaces
2004
Speech-based applications commonly come with web-based or printed manuals. Alternatively, the dialogue can be designed so that users should be able to start using the application on their own. We studied an alternative approach, an integrated tutor. The tutor participates in the interaction when new users learn to use a speech-based system. It teaches the users how to operate the system and monitors user actions to be certain that the users do indeed learn. In this paper we describe our experiences with the design and the iterative development of an integrated tutor. Expert evaluation and two user tests were conducted with different versions of the tutor. The results show that the tutor can effectively guide new users. We identify the six most important lessons learned, the most important being that it is essential to spot problems by monitoring user actions, especially when novice users are tutored.
VOICE ASSISTANTS AS A TRAINING TOOL IN A FOREIGN LANGUAGE CLASS final
2019
This article covers the didactic potential of the intelligent personal assistants (voice assistants) for reaching the communicative competence during the foreign language acquisition. The authors of the article emphasize that the variety of modern voice assistants embedded to the users’ personal devices (such as Siri, Google Assistant, etc.) and available for teachers as tools is necessary to study in detail since their functions and communicative abilities (although they have some visible similarities) nevertheless differ. These differences become especially distinctly when we use these “programs” at the foreign language classes. To illustrate that, authors describe particularly one of the newest voice assistants’ educational potential, the Russian assistant of Yandex – Alice, in Russian as a foreign language class. The article outlines the differences that Alice has with the analog voice assistants and describes its didactic capacities, as well as how they can be used from the very beginning of language learning. The authors of the research also present a system of the exercises with Alice that supplements the blended language learning model for the beginners. The system of the exercises was tested during teaching Russian in several multinational students’ groups and the results of the experiment are represented in the study in detail. Keywords: teaching foreign languages, teaching Russian as a foreign language, mobile learning, virtual assistant, voice assistants.
Developing and Evaluating Conversational Agents
2000
Conversation agents present a challenging agenda for research and application. We describe the development, evaluation, and application of Baldi, a computer animated talking head. Baldi's existence is justified by the important contribution of the face in spoken dialog. His actions are evaluated and modified to mimic natural actions as much as possible. Baldi has the potential to enrich human-machine interactions and serve as a tutor in a wide variety of educational domains. We describe one current application of language tutoring with children with hearing loss.
Proceedings of the 5th International Conference on Conversational User Interfaces
Conversation design at least partly aspires to create Voice User Interfaces which emulate human speech production. And yet, there is no established approach for the development of naturalistic conversational infrastructure for VUIs; conversation designers are advised to work from their common sense understanding of conversation, producing written scripts, based on memory and imagination, which are later converted into speech. This is a shortcoming in conversation design which needs to be addressed. In this provocation paper, we argue that the starting point in the development of any VUI should be the examination of natural spoken conversation, preferably from the same interactional context in which the VUI will be deployed. We provide a short example to illustrate how the current process of conversation scriptwriting can be a barrier to this, and demonstrate how this can be overcome using the social scientific approach of Conversation Analysis (CA). CCS CONCEPTS • Computing methodologies → Artificial intelligence; Natural language processing; Discourse, dialogue and pragmatics; • Human-centered computing → Interaction design; Interaction design, theory, concepts and paradigms.
Exploring AI language assistants with primary EFL students
CALL in a climate of change: adapting to turbulent global conditions – short papers from EUROCALL 2017, 2017
The main objective of this study was to identify ways to incorporate voice-driven Artificial Intelligence (AI) effectively in classroom language learning. This nine month teacher-led design research study employed technology probes (Amazon's Alexa, Apple's Siri, Google voice search) and co-design methods with a class of primary age English as a Foreign Language (EFL) students to explore and develop ideas for classroom activities using AI language assistants. Speaking to AI assistants was considered highly engaging by all students. Students were observed to speak more English when using AI assistants in group work, and to spontaneously reformulate, self-correct, and joyfully and playfully persist with speaking English in their attempts to get AI assistants to do what they wanted them to do.