LeCycl22: Delivering Sensing Technologies for Education and Learning

Paper Program

Takumi Nakai, Andrew Vargo, and Koichi Kise: "Attaching Microlearning to Existing Habits"

Abstract: To take advantage of microlearning, it is desirable for learners to make microlearning a habit. Most of the conventional methods for making microlearning a habit are intended to form a habit from scratch, but attempts to form a habit from scratch require a lot of motivation and workload from the learner. In this study, we propose habit-attached microlearning as a method to make microlearning a habit with less burden. This method designs a mechanism in which a microlearning task is added to the learner's existing habits. In this study, we focused on web browsing on smartphones as a habit to attach to learning, and developed a web browsing application for learning English vocabulary. This paper reports on a controlled experiment conducted to evaluate the learning and habit-forming effects of the developed application.


Kyungho Lee: "Designing an Intelligent Learning System for Practicing the Oboe Embouchure"

Abstract: The oboe is considered one of the most difficult woodwind instruments to learn due to the labor involved in mastering the embouchure required to produce a steady, long tone through the instrument’s reeds. Previous research in music education has suggested that using visualization or imagery as a training method, so-called audiation, helps novice learners gain a better understanding of the relationship between sound and embouchure. Inspired by this concept, we designed an interactive learning system using real-time acoustic analysis (MFCCs) and support vector machines (SVM). Our interactive visualization aims to support the user’s learning process by rendering the quality of good and bad sounds as pitch indications through particle swarm animations. A pilot user study showed that this makes the learning experience more reflective and self-directed, as the learner can understand the relationship between their breathing technique and the visualization of the generated sound quality. In this paper, we intend to address issues potentially involved in designing an intelligent learning system using sensing technologies in the context of music education.


Ralph Rose, Naho Orita, Ayaka Sugawara, Qiao Wang: "Evaluation Dataset of Multiple-Choice Cloze Items for Vocabulary Training and Testing"

Abstract: Vocabulary learning is a typical part of nearly any second language learning curriculum. This entails methodologies and materials for training and testing vocabulary knowledge in learners. In large-scale programs, the preparation of such materials can be labor intensive and thus automatic means of generation are desirable. VocaTT (Vocabulary Training and Testing) is an ongoing project to use machine learning methods to generate novel multiple choice cloze (i.e., fill-in-the-blank) items for use in second language learning programs. This paper describes the ongoing creation of a gold standard set of multiple-choice cloze items to be used in training a machine learning algorithm. Machine-generated multiple choice cloze items were reviewed by two experienced language teachers, who evaluated each item for well-formedness (i.e., suitability as multiple-choice cloze test item) with three options: reject as unsalvageable, keep as-is, or revise into a well-formed item as they thought best. Results for a 600-item set that both checkers evaluated show moderate agreement on the question of rejection but slight agreement for keeping as-is. For revised items, the agreement on what type of revisions to make was slight to fair. In an expanded set of 2,792 items, checkers judged most items as needing revision but made varying kinds of revisions to yield well-formed items. Interested researchers may contact the authors to inquire about how they may access and use the evaluation dataset.


Hamraz Javaheri, Jessica Lehmann, Kristin Altmeyer, Lea Marie Müller, Roland Brünken, and Paul Lukowicz: "Design of augmented reality based environment to promote spatial imagination for mathematics education in elementary school"

Abstract: This paper investigates the use of augmented reality (AR) technology to deliver augmented lectures to support students in acquiring the curricular competency of using spatial imagination in mathematics education. As a very important stage in education to develop spatial abilities this paper focuses on elementary school children. Due to the challenges of working with children in experimental studies, this education level has received comparatively little attention in terms of support through ubiquitous technology. A theory-driven design approach was adopted in the development of an AR-based learning environment to visualize various virtual 3D cube buildings aligned with real blueprints. The designed environment was evaluated by a group of 1st and 2nd grade students in terms of system usability. The results showed that the theory-driven design was successful with a score of 86.56 on the System Usability test. In our future work, we aimed to assess the effectiveness of the proposed AR environment in terms of learning gains by performing more task-focused studies before and after experiment and comparing the results with the traditional teaching methods.


Hannah Nolasco, Andrew Vargo, and Koichi Kise: "Mixed-Methods Self-Tracking: Qualitative Styles of Quantifying the Self"

Abstract: Self-tracking technologies face inconsistent reactions from users that range from excitement and enthusiasm to frustration and discomfort. Many of those on the latter end of this spectrum deal with complex feelings of disempowerment and objectification; they also face adverse effects from the excessive quantification of their lived experiences. Rather than serve as active agents in their process of monitoring and improving themselves, users feel reduced to docile spectators who are coerced into changing their behavior. This position paper explores the tensions in power redistribution and depersonalization present in existing self-tracking methods and contemplates on qualitative alternatives that may improve the design of future technologies, particularly in the field of learning.


Mathilde Hutin, Sofiya Kobylyanskaya, and Laurence Devillers: "Nudges in Technology-Mediated Knowledge Transfer: Two Experimental Designs"

Abstract: Recent advances in technologies now allow us to learn almost anything in virtual environments, be it via Internet forums or websites, telephone apps, video games, and many more. Such technology-mediated learning can be enhanced with the use of embedded nudges, i.e., devices in the architecture of choice to encourage (\textit{nudge}) the users towards one choice rather than the other without limiting their freedom of choice. This paper presents an overview of how nudges can help improve knowledge acquisition, as well as a two ongoing projects. Ethical issues are also highlighted.


Hugo Le Tarnec, Olivier Augereau, Elisabetta Bevacqua, and Pierre De Loor: "Improving collaborative learning in virtual reality with facial expressions"

Abstract: This article presents an approach to improve collaborative learning in terms of performance and satisfaction through the generation of non-verbal behavior of users displayed on their avatar in virtual reality. Various works have focused on the behavioral realism of avatars, which can considerably improve interactions. The purpose of this paper is to investigate the impact of displaying the facial expressions of a user in real time on the performance of the task, the satisfaction and the behavioral changes of the users interacting in a virtual environment. To evaluate this approach, we carried out a study where the users collaborated to build a TV stand in dyad including a novice (the participant) and an expert assistant (the experimenter). 


Junaid Younas and Paul Lukowicz: "Cognitive Ability Classification using On-body Sensors"

Abstract: This work presents an on-body sensor setup to keep track of the learning progress while performing cognitive activities in formal education. The proposed approach uses the sensor collected data for cognitive ability classification, i.e., confidence score, cognitive load, and expertise, while attempting to solve physics-related problems. Data is collected using a combination of instruction material, an eye-tracker, and a sensor pen to capture the cognition progress. The collected data is processed and transformed to feature representation using a novel feature-set presented in this paper for learning analytics. The used features help to highlight the difference in learner's cognitive abilities and enable teachers to cater to individual needs and requirements, an essential aspect of need-based learning. 


Haruki Suzawa, Ko Watanabe, Masakazu Iwamura, Koichi Kise, Andreas Dengel, and Shoya Ishimaru: "Supporting Smooth Interruption in a Video Conference by Dynamically Changing Background Music Depending on the Amount of Utterance"

Abstract: Interrupting a speaker at the right moment during a meeting is an advanced skill, and not everyone can do it. It is not a rare case that one person keeps talking for a long time, particularly in a video conference, due to limited bandwidth and latency. In order to solve this problem, this paper presents a proof of concept and a working prototype of DiscussionJockey, an online meeting bot that measures the amount of speech of each meeting participant and provides an acoustic stimulus selected by the measurement. On the basis of a literature review, we hypothesized that the timing of speech can be implicitly manipulated by playing background music (BGM) with specific beats per minute (BPM). We conducted a pilot study using the proposed system and observed it made the utterance rate of participants closer to each other. The result of this pilot study has revealed the potential and challenges of meeting interventions.


Kanta Yamaoka, Ko Watanabe, Koichi Kise, Andreas Dengel, and Shoya Ishimaru: "Experience is the Best Teacher: Personalized Vocabulary Building Within the Context of Instagram Posts and Sentences from GPT-3"

Abstract: Although language learners have different contexts and motivations, sensing personal backgrounds to optimize learning materials has still been challenging. By focusing on the huge movement of Social Networking Services (SNS) such as Instagram, we came up with the idea of utilizing social posts, in particular images, as learning materials. This paper presents our working prototype of the proposed system that extracts keywords from these images and leverages GPT-3 to generate sentences for acquiring new vocabulary around the keywords. By conducting a pilot study involving three users, we found that 2.2 words appeared as unknown words for the user in one generated sentence on average, and there is room for improvement in the proposed system. These findings can be utilized in a large-scale evaluation designed in the future.