Language learning applications usually estimate the learner’s language knowledge over time to provide personalized practice content for each learner at the optimal timing. However, accurately predicting language knowledge or linguistic skills is much more challenging than math or science knowledge, as many language tasks involve memorization and retrieval. Learners must memorize a large number of words and meanings, which are prone to be forgotten without practice. Although a few studies consider forgetting when modeling learners’ language knowledge, they tend to apply traditional models, consider only partial information about forgetting, and ignore linguistic features that may significantly influence learning and forgetting. This article focuses on modeling and predicting learners’ knowledge by considering their forgetting behavior and linguistic features in language learning. Specifically, we first explore the existence of forgetting behavior and cross-effects in real-world language learning datasets through empirical studies. Based on these, we propose a model for predicting the probability of recalling a word given a learner’s practice history. The model incorporates (1) three types of key information related to forgetting (time-gap, interaction, and word features), (2) question formats, and (3) similarities between words using the attention mechanism. Extensive experiments on two real-world datasets show that the proposed model improves performance compared to baselines. Moreover, the results indicate that combining multiple types of forgetting information and item format improves performance. In addition, we find that incorporating semantic and morphological features, such as word embeddings, to model similarities between words in a learner’s practice history and their effects on memory also improves the model. Our work indicates a potential future research direction for the knowledge tracing task in second language acquisition, which gives more instructive results for enhancing learning and teaching.

Motivated by the rapid technological advancements achieved in the last five years and the pervasiveness of Artificial Intelligence (AI), this paper investigates the evolving role of HCI and revisits the seven grand challenges outlined in 2019: human-technology symbiosis, human-environment interactions, ethics, privacy and security, well-being, health and eudaimonia, accessibility and universal access, learning and creativity, and social organization and democracy. Through literature analysis, the paper reevaluates the status of each challenge and highlights emerging requirements. Key findings reveal the widespread impact of AI across all domains and emphasize the need for improved AI transparency, alignment with human values, and the development of explainable, personalized, and privacy-preserving technologies to enhance user trust and control. The analysis also highlights the interconnected nature of these challenges and firmly asserts the role of technology in actively supporting human activities and collaborating harmoniously with humans to help them live meaningfully and fulfill aspirations.

Course recommender systems can assist students in identifying suitable or appealing courses by leveraging user interaction data. However, a prevalent issue with existing course recommender systems is their tendency to prioritize accuracy over explainability. To address this limitation, we propose a novel Knowledge Entity-Aware Model for course recommendation called KEAM, which supports explicit user profile generation based on detailed information from a knowledge graph to enhance comprehension of the students. Specifically, we exploit the information within knowledge graphs using neural networks. Then, KEAM captures students' preferences and creates profiles for explainable recommendations. Comprehensive experiments are conducted on two datasets to verify the effectiveness and explainability of KEAM.

Completing a motion sequence based on sparse key-frames remains a challenging task. The limited grasp of the human skeleton's spatial structure and the complexity of handling sparsely distributed motion sequences pose challenges for traditional interpolation algorithms, hindering their ability to generate authentic and smooth results. Recent progress utilizes Graph Convolutional Networks (GCN) to analyze human skeleton data, yielding promising results. In this paper, we introduce an improved Attention-Based Graph Convolutional Network framework for motion completion that tackles two key challenges: modeling correlations across indirectly connected joints and modeling correlations across frames in motion sequences with diverse sparsity. The method is designed to augment the learning capability of the GCN-based model without being constrained by the inherent human skeleton structure. Furthermore, this design can be concurrently applied to scenarios involving the completion of both single-person and multi-person motions. Experimental results on public human action datasets NTU RGB-D affirm the Spatio-Temporal Attention-Based Graph Convolutional Network's ability to generate smooth and authentic motion results.

In recent years, there has been a growing interest in the application of Graph Convolutional Networks (GCNs) for classifying or generating human skeleton-based action sequences. Despite the progress in this field, there exists a relative dearth of research on the underlying mechanisms of how these network structures learn and represent the information features of the human skeleton. This paper proposes a novel GCN-based reconstruction network ST-ATGCN that utilizes spatial and temporal attention mechanisms for analyzing the extraction and reconstruction patterns of human action sequences. This versatile network can be effectively employed in a wide array of applications, including data compression, noise reduction, and interpolation. Experimental results on a public dataset demonstrate that ST-ATGCN network outperforms most of the currently prevailing GCN-based methods. This indicates the efficacy of the proposed network architecture in accurately extracting and reconstructing human skeleton information. Moreover, the reconstruction network exhibits proficiency in effectively restoring noisy action sequences.

Abstract In this paper, we propose a cross-language font style transfer system that can synthesize a new font by observing only a few samples from another language. Automatic font synthesis is a challenging task and has attracted much research interest. Most previous works addressed this problem by transferring the style of the given subset to the content of unseen ones. Nevertheless, they only focused on the font style transfer in the same language. In many cases, we need to learn font style from one language and then apply it to other languages. Existing methods make this difficult to accomplish because of the abstraction of style and language differences. To address this problem, we specifically designed the network into a multi-level attention form to capture both local and global features of the font style. To validate the generative ability of our model, we constructed an experimental font dataset of 847 fonts, each containing English and Chinese characters with the same style. Results show that our model generates 80.3% of users’ preferred images compared with state-of-the-art models.

In this paper, we propose a novel model FTransGAN that can transfer font styles between different languages by observing only a few samples. The automatic generation of a new font library is a challenging task and has been attracting many researchers' interests. Most previous works addressed this problem by transferring the style of the given subset to the content of unseen ones. Nevertheless, they only focused on the font style transfer in the same language. In many tasks, we need to learn the font information from one language and then apply it to other languages. It's difficult for the existing methods to do such tasks. To solve this problem, we specifically design our network into a multi-level attention form to capture both local and global features of the style images. To verify the generative ability of our model, we construct an experimental font dataset which includes 847 fonts, each of them containing English and Chinese characters with the same style. Experimental results show that compared with the state-of-the-art models, our model generates 80.3% of all user preferred images.

Extended learning support systems for all-age education requires inclusive user interface design, especially for elderly users. A dual-tablet user interface with simplified visual layers and more intuitive operations was proposed aiming to reduce the physical and mental loads of elderly learners. An initial prototype with basic functions of viewing learning material was developed based on a cross-platform framework. Two preliminary user experiments participated by elderly volunteers were carried out for formative evaluations, in order to improve the usability of the interface design iteratively. The prototype was modified based on the participants' comments and observation of their operations during the experiments. Additional findings of the elderly users' preference and tendency were discussed for further development.

To improve designs of e-learning materials, it is necessary to know which word or figure a learner felt "difficult" in the materials. In this pilot study, we measured electroencephalography (EEG) and eye gaze data of learners and analyzed to estimate which area they had difficulty to learn. The developed system realized simultaneous measurements of physiological data and subjective evaluations during learning. Using this system, we observed specific EEG activity in difficult pages. Integrating of eye gaze and EEG measurements raised a possibility to determine where a learner felt "difficult" in a page of learning materials. From these results, we could suggest that the multimodal measurements of EEG and eye gaze would lead to effective improvement of learning materials. For future study, more data collection using various materials and learners with different backgrounds is necessary. This study could lead to establishing a method to improve e-learning materials based on learners' mental states.

Published with license by Taylor & Francis Group, LLC. This article aims to investigate the Grand Challenges which arise in the current and emerging landscape of rapid technological evolution towards more intelligent interactive technologies, coupled with increased and widened societal needs, as well as individual and collective expectations that HCI, as a discipline, is called upon to address. A perspective oriented to humane and social values is adopted, formulating the challenges in terms of the impact of emerging intelligent interactive technologies on human life both at the individual and societal levels. Seven Grand Challenges are identified and presented in this article: Human-Technology Symbiosis; Human-Environment Interactions; Ethics, Privacy and Security; Well-being, Health and Eudaimonia; Accessibility and Universal Access; Learning and Creativity; and Social Organization and Democracy. Although not exhaustive, they summarize the views and research priorities of an international interdisciplinary group of experts, reflecting different scientific perspectives, methodological approaches and application domains. Each identified Grand Challenge is analyzed in terms of: concept and problem definition; main research issues involved and state of the art; and associated emerging requirements. BACKGROUND This article presents the results of the collective effort of a group of 32 experts involved in the community of the Human Computer Interaction International (HCII) Conference series. The group’s collaboration started in early 2018 with the collection of opinions from all group members, each asked to independently list and describe five HCI grand challenges. During a one-day meeting held on the 20th July 2018 in the context of the HCI International 2018 Conference in Las Vegas, USA, the identified topics were debated and challenges were formulated in terms of the impact of emerging intelligent interactive technologies on human life both at the individual and societal levels. Further analysis and consolidation led to a set of seven Grand Challenges presented herein. This activity was organized and supported by the HCII Conference series.

Low back pain (LBP) is a globally common condition with no silver bullet solutions. Further, the lack of therapeutic consensus causes challenges in choosing suitable solutions to try. In this work, we crowdsourced knowledge bases on LBP treatments. The knowledge bases were used to rank and offer best-matching LBP treatments to end users. We collected two knowledge bases: one from clinical professionals and one from non-professionals. Our quantitative analysis revealed that non-professional end users perceived the best treatments by both groups as equally good. However, the worst treatments by non-professionals were clearly seen as inferior to the lowest ranking treatments by professionals. Certain treatments by professionals were also perceived significantly differently by non-professionals and professionals themselves. Professionals found our system handy for self-reflection and for educating new patients, while non-professionals appreciated the reliable decision support that also respected the non-professional opinion.

We propose a new change detection method using clickstream data collected through an e-Book system. Most of the prior work has focused on the batch processing of clickstream data. In contrast, the proposed method is designed for online processing, with the model parameters for change detection updated sequentially based on observations of new click events. More specifically, our method generates a model for an individual student and performs minute-by-minute change detection based on click events during a classroom lecture. We collected clickstream data from four face-to-face lectures, and conducted experiments to demonstrate how the proposed method discovered change points and how such change points correlated with the students' performances.

Online crowdsourcing enables the distribution of work to a global labor force as small and often repetitive tasks. Recently, situated crowdsourcing has emerged as a complementary enabler to elicit labor in specific locations and from specific crowds. Teamwork in online crowdsourcing has been recently shown to increase the quality of output, but teamwork in situated crowdsourcing remains unexplored. We set out to fill this gap. We present a generic crowdsourcing platform that supports situated teamwork and provide experiences from a laboratory study that focused on comparing traditional online crowdsourcing to situated team-based crowdsourcing. We built a crowdsourcing desk that hosts three networked terminal displays. The displays run our custom team-driven crowdsourcing platform that was used to investigate collocated crowdsourcing in small teams. In addition to analyzing quantitative data, we provide findings based on questionnaires, interviews, and observations. We highlight 1) emerging differences between traditional and collocated crowdsourcing, 2) the collaboration strategies that teams exhibited in collocated crowdsourcing, and 3) that a priori team familiarity does not significantly affect collocated interaction in crowdsourcing. The approach we introduce is a novel multi-display crowdsourcing setup that supports collocated labor teams and along with the reported study makes specific contributions to situated crowdsourcing research.

We propose crowd replication as a low-effort, easy to implement and cost-effective mechanism for quantifying the uses, activities, and sociability of public spaces. Crowd replication combines mobile sensing, direct observation, and mathematical modeling to enable resource efficient and accurate quantification of public spaces. The core idea behind crowd replication is to instrument the researcher investigating a public space with sensors embedded on commodity devices and to engage him/her into imitation of people using the space. By combining the collected sensor data with a direct observations and population model, individual sensor traces can be generalized to capture the behavior of a larger population. We validate the use of crowd replication as a data collection mechanism through a field study conducted within an exemplary metropolitan urban space. Results of our evaluation show that crowd replication accurately captures real human dynamics (0.914 correlation between indicators estimated from crowd replication and visual surveillance) and captures data that is representative of the behavior of people within the public space.

A warm welcome to the Twelfth Annual IEEE International Conference on Pervasive Computing and Communications (PerCom 2014). We are pleased to introduce the technical program of the conference which this year includes 25 papers representing high-quality research conducted over a broad spectrum of topics related to pervasive computing.

As people visit various places in their daily lives, connections are formed between people via places (co-presence), and between places via people (overlapping). This paper introduces a method for modeling social and geographical context based on colocation networks in human mobility datasets. Applying the method to a metropolitan-scale mobility dataset reveals a variety of place groups that can be considered in the design of urban ubicomp applications.

To seek and collect useful sensor data in a participatory sensing environment, participants should be able to coordinate their activities in a timely manner. However, existing systems deal separately with the "preparation time" to define the goal and method of sensing, and the "sensing time" in the field. Therefore, participants cannot easily modify the sensing method, including the collaboration setting, once they are out in the field. In this demonstration, we will present a system called Kitokito, which allows participants to easily create small sensing tasks, and iteratively modify the collaboration and sensing method during the "sensing time."

Recent mobile devices are integrated with various kinds of sensors, thereby allowing people to capture what stationary sensing devices cannot easily acquire. We term the systems that exploit the ubiquity of the users of such devices Human Probes. To realize a Human-Probe environment, our research group has examined the usefulness of pressure sensors embedded in shoes [2]. In this demonstration, we present our recent work that extends our previous research on embedded pressure sensors by considering complimentary uses of accelerometers so as to measure walkability in our everyday spaces. Pressure sensors and accelerometers are similarly useful for capturing the motion of pedestrians; however, the close examination of the signals from both sensors reveals the strengths and the weaknesses of each, and suggests the possibility of their complimentary use to support Human Probes.

Ad hoc networks enable application services in various environments including indoor/underground spaces and urban canyons; however conventional positioning infrastructures such as the GPS generally do not work well in these environments. We propose a lightweight, RFED-based positioning system that can be installed quickly and easily at various sites of ad hoc application deployment. The system includes a novel device called RFID Tape, which allows for efficient deployment and maintenance of a series of RFID location reference points. Pedestrian devices obtain location information from RFID reference points, and use motion sensors and a P2P-based technique to allow for continuous positioning even when the reference points are sparse. The device and the mechanism together facilitate the provision of location-aware features in ad hoc applications.

In this paper, we analyze security and privacy issues in RFID-based reference point systems, which seamlessly provide high resolution location information so as to enable innovative mobile applications. Our preliminary analysis revealed the significance of the labor cost in deploying RFID reference points; therefore, we carefully analyze several system architecture candidates in terms of deployment cost and security/privacy threats. Based on the analysis, we select a scalable architecture to avoid the bottleneck in deployment cost even though it can be less secure. Finally, we briefly discuss potential solutions for critical security and privacy issues in the selected architecture.

S.120-127

Distributed multi-user hypermedia environments provide not only information-sharing mechanisms but also user collaboration/communication facilities. The provision of integrated views of heterogeneous information resources is necessary to create a common understanding among the users, who are possibly distributed in terms of geography and time. However, the requirements of customization must also be considered, since such diverse users would want to personalize their views of shared information. In order to integrate these views while considering the requirements of flexible customization, we propose cooperative view mechanisms of Dexter-based hypermedia systems, introducing environmental objects and their participation relationships. The mechanisms instantiate hypermedia deputies on the screen using participation relationships of the users, hypermedia components and environments. The relationships are also used for the purpose of supporting awareness. Using a novel user collaboration facility, the relationships are visualized so that users can easily recognize other users and/or user groups having the same, slightly different or very different views. Attributes of environment objects are discussed so that the mechanisms can be effectively utilized in computer-supported cooperative work settings such as distance presentations, virtual offices and virtual classrooms.