arXiv subjects

Xiaojuan Ma

Publications and source records attributed to Xiaojuan Ma.

At least 91 records · Page 5Linked to original sources

arXiv2022

Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset

Automatic speech recognition (ASR) on low resource languages improves the access of linguistic minorities to technological advantages provided by artificial intelligence (AI). In this paper, we address the problem of data scarcity for the Hong Kong Cantonese language by creating a new Cantonese dataset. Our dataset, Multi-Domain Cantonese Corpus (MDCC), consists of 73.6 hours of clean read speech paired with transcripts, collected from Cantonese audiobooks from Hong Kong. It comprises philosophy, politics, education, culture, lifestyle and family domains, covering a wide range of topics. We also review all existing Cantonese datasets and analyze them according to their speech type, data source, total size and availability. We further conduct experiments with Fairseq S2T Transformer, a state-of-the-art ASR model, on the biggest existing dataset, Common Voice zh-HK, and our proposed MDCC, and the results show the effectiveness of our dataset. In addition, we create a powerful and robust Cantonese ASR model by applying multi-dataset learning on MDCC and Common Voice zh-HK.

cs.CL↗

arXiv2021

Understanding Players' Interaction Patterns with Mobile Game App UI via Visualizations

Understanding how players interact with the mobile game app on smartphone devices is important for game experts to develop and refine their app products. Conventionally, the game experts achieve their purposes through intensive user studies with target players or iterative UI design processes, which can not capture interaction patterns of large-scale individual players. Visualizing the recorded logs of users' UI operations is a promising way for quantitatively understanding the interaction patterns. However, few visualization tools have been developed for mobile game app interaction, which is challenging with multi-touch dynamic operations and complex UI. In this work, we fill the gap by presenting a visualization approach that aims to understand players' interaction patterns in a multi-touch gaming app with more complex interactions supported by joysticks and a series of skill buttons. Particularly, we identify players' dynamic gesture patterns, inspect the similarities and differences of gesture behaviors, and explore the potential gaps between the current mobile game app UI design and the real-world practice of players. Three case studies indicate that our approach is promising and can be potentially complementary to theoretical UI designs for further research.

cs.HC↗

arXiv2021

Human-Centered AI for Data Science: A Systematic Approach

Human-Centered AI (HCAI) refers to the research effort that aims to design and implement AI techniques to support various human tasks, while taking human needs into consideration and preserving human control. In this short position paper, we illustrate how we approach HCAI using a series of research projects around Data Science (DS) works as a case study. The AI techniques built for supporting DS works are collectively referred to as AutoML systems, and their goals are to automate some parts of the DS workflow. We illustrate a three-step systematical research approach(i.e., explore, build, and integrate) and four practical ways of implementation for HCAI systems. We argue that our work is a cornerstone towards the ultimate future of Human-AI Collaboration for DS and beyond, where AI and humans can take complementary and indispensable roles to achieve a better outcome and experience.

cs.LG↗

arXiv2021

Inspecting the Process of Bank Credit Rating via Visual Analytics

Bank credit rating classifies banks into different levels based on publicly disclosed and internal information, serving as an important input in financial risk management. However, domain experts have a vague idea of exploring and comparing different bank credit rating schemes. A loose connection between subjective and quantitative analysis and difficulties in determining appropriate indicator weights obscure understanding of bank credit ratings. Furthermore, existing models fail to consider bank types by just applying a unified indicator weight set to all banks. We propose RatingVis to assist experts in exploring and comparing different bank credit rating schemes. It supports interactively inferring indicator weights for banks by involving domain knowledge and considers bank types in the analysis loop. We conduct a case study with real-world bank data to verify the efficacy of RatingVis. Expert feedback suggests that our approach helps them better understand different rating schemes.

cs.LG↗

arXiv2021

Student Barriers to Active Learning in Synchronous Online Classes: Characterization, Reflections, and Suggestions

As more and more face-to-face classes move to online environments, it becomes increasingly important to explore any emerging barriers to students' learning. This work focuses on characterizing student barriers to active learning in synchronous online environments. The aim is to help novice educators develop a better understanding of those barriers and prepare more student-centered course plans for their active online classes. Towards this end, we adopt a qualitative research approach and study information from different sources: social media content, interviews, and surveys from students and expert educators. Through a thematic analysis, we craft a nuanced list of students' online active learning barriers within the themes of human-side, technological, and environmental barriers. Each barrier is explored from the three aspects of frequency, importance, and exclusiveness to active online classes. Finally, we conduct a summative study with 12 novice educators and explain the benefits of using our barrier list for course planning in active online classes.

cs.HC↗

arXiv2021

Optimizing Fund Allocation for Game-based Verifiable Computation Outsourcing

This paper considers the setting where a cloud server services a static set or a dynamic sequence of tasks submitted by multiple clients. Every client wishes to assure honest execution of tasks by additionally employing a trusted third party (TTP) to re-compute the tasks with a certain probability. The cloud server makes a deposit for each task it takes, each client allocates a budget (including the wage for the server and the cost for possibly hiring TTP) for each task submitted, and every party has its limited fund for either deposits or task budgets. We study how to allocate the funds optimally to achieve the three-fold goals: a rational cloud server honestly computes each task; the server's wage is maximized; the overall delay for task verification is minimized. We apply game theory to formulate the optimization problems, and develop the optimal or heuristic solutions for three application scenarios. For each of the solutions, we analyze it through either rigorous proofs or extensive simulations. To the best of our knowledge, this is the first work on optimizing fund allocation for verifiable outsourcing of computation in the setting of one server and multiple clients, based on game theory.

cs.GT↗

arXiv2021

CASS: Towards Building a Social-Support Chatbot for Online Health Community

Chatbots systems, despite their popularity in today's HCI and CSCW research, fall short for one of the two reasons: 1) many of the systems use a rule-based dialog flow, thus they can only respond to a limited number of pre-defined inputs with pre-scripted responses; or 2) they are designed with a focus on single-user scenarios, thus it is unclear how these systems may affect other users or the community. In this paper, we develop a generalizable chatbot architecture (CASS) to provide social support for community members in an online health community. The CASS architecture is based on advanced neural network algorithms, thus it can handle new inputs from users and generate a variety of responses to them. CASS is also generalizable as it can be easily migrate to other online communities. With a follow-up field experiment, CASS is proven useful in supporting individual members who seek emotional support. Our work also contributes to fill the research gap on how a chatbot may influence the whole community's engagement.

cs.HC↗

arXiv2021

Characterizing Student Engagement Moods for Dropout Prediction in Question Pool Websites

Problem-Based Learning (PBL) is a popular approach to instruction that supports students to get hands-on training by solving problems. Question Pool websites (QPs) such as LeetCode, Code Chef, and Math Playground help PBL by supplying authentic, diverse, and contextualized questions to students. Nonetheless, empirical findings suggest that 40% to 80% of students registered in QPs drop out in less than two months. This research is the first attempt to understand and predict student dropouts from QPs via exploiting students' engagement moods. Adopting a data-driven approach, we identify five different engagement moods for QP students, which are namely challenge-seeker, subject-seeker, interest-seeker, joy-seeker, and non-seeker. We find that students have collective preferences for answering questions in each engagement mood, and deviation from those preferences increases their probability of dropping out significantly. Last but not least, this paper contributes by introducing a new hybrid machine learning model (we call Dropout-Plus) for predicting student dropouts in QPs. The test results on a popular QP in China, with nearly 10K students, show that Dropout-Plus can exceed the rival algorithms' dropout prediction performance in terms of accuracy, F1-measure, and AUC. We wrap up our work by giving some design suggestions to QP managers and online learning professionals to reduce their student dropouts.

cs.HC↗

arXiv2020

QLens: Visual Analytics of Multi-step Problem-solving Behaviors for Improving Question Design

With the rapid development of online education in recent years, there has been an increasing number of learning platforms that provide students with multi-step questions to cultivate their problem-solving skills. To guarantee the high quality of such learning materials, question designers need to inspect how students' problem-solving processes unfold step by step to infer whether students' problem-solving logic matches their design intent. They also need to compare the behaviors of different groups (e.g., students from different grades) to distribute questions to students with the right level of knowledge. The availability of fine-grained interaction data, such as mouse movement trajectories from the online platforms, provides the opportunity to analyze problem-solving behaviors. However, it is still challenging to interpret, summarize, and compare the high dimensional problem-solving sequence data. In this paper, we present a visual analytics system, QLens, to help question designers inspect detailed problem-solving trajectories, compare different student groups, distill insights for design improvements. In particular, QLens models problem-solving behavior as a hybrid state transition graph and visualizes it through a novel glyph-embedded Sankey diagram, which reflects students' problem-solving logic, engagement, and encountered difficulties. We conduct three case studies and three expert interviews to demonstrate the usefulness of QLens on real-world datasets that consist of thousands of problem-solving traces.

cs.HC↗

arXiv2020

A Visual Analytics Approach to Scheduling Customized Shuttle Buses via Perceiving Passengers' Travel Demands

Shuttle buses have been a popular means to move commuters sharing similar origins and destinations during periods of high travel demand. However, planning and deploying reasonable, customized service bus systems becomes challenging when the commute demand is rather dynamic. It is difficult, if not impossible to form a reliable, unbiased estimation of user needs in such a case using traditional modeling methods. We propose a visual analytics approach to facilitating assessment of actual, varying travel demands and planning of night customized shuttle systems. A preliminary case study verifies the efficacy of our approach.

cs.HC↗

arXiv2020

Friend Network as Gatekeeper: A Study of WeChat Users' Consumption of Friend-Curated Contents

Social media enables users to publish, disseminate, and access information easily. The downside is that it has fewer gatekeepers of what content is allowed to enter public circulation than the traditional media. In this paper, we present preliminary empirical findings from WeChat, a popular messaging app of the Chinese, indicating that social media users leverage their friend networks collectively as latent, dynamic gatekeepers for content consumption. Taking a mixed-methods approach, we analyze over seven million users' information consumption behaviors on WeChat and conduct an online survey of $216$ users. Both quantitative and qualitative evidence suggests that friend network indeed acts as a gatekeeper in social media. Shifting from what should be produced that gatekeepers used to decide, friend network helps separate the worthy from the unworthy for individual information consumption, and its structure and dynamics that play an important role in gatekeeping may inspire the future design of socio-technical systems.

cs.SI↗

arXiv2020

Investigating the Effects of Robot Engagement Communication on Learning from Demonstration

Robot Learning from Demonstration (RLfD) is a technique for robots to derive policies from instructors' examples. Although the reciprocal effects of student engagement on teacher behavior are widely recognized in the educational community, it is unclear whether the same phenomenon holds true for RLfD. To fill this gap, we first design three types of robot engagement behavior (attention, imitation, and a hybrid of the two) based on the learning literature. We then conduct, in a simulation environment, a within-subject user study to investigate the impact of different robot engagement cues on humans compared to a "without-engagement" condition. Results suggest that engagement communication significantly changes the human's estimation of the robots' capability and significantly raises their expectation towards the learning outcomes, even though we do not run actual learning algorithms in the experiments. Moreover, imitation behavior affects humans more than attention does in all metrics, while their combination has the most profound influences on humans. We also find that communicating engagement via imitation or the combined behavior significantly improve humans' perception towards the quality of demonstrations, even if all demonstrations are of the same quality.

cs.HC↗

arXiv2020

VoiceCoach: Interactive Evidence-based Training for Voice Modulation Skills in Public Speaking

The modulation of voice properties, such as pitch, volume, and speed, is crucial for delivering a successful public speech. However, it is challenging to master different voice modulation skills. Though many guidelines are available, they are often not practical enough to be applied in different public speaking situations, especially for novice speakers. We present VoiceCoach, an interactive evidence-based approach to facilitate the effective training of voice modulation skills. Specifically, we have analyzed the voice modulation skills from 2623 high-quality speeches (i.e., TED Talks) and use them as the benchmark dataset. Given a voice input, VoiceCoach automatically recommends good voice modulation examples from the dataset based on the similarity of both sentence structures and voice modulation skills. Immediate and quantitative visual feedback is provided to guide further improvement. The expert interviews and the user study provide support for the effectiveness and usability of VoiceCoach.

cs.HC↗

arXiv2019

Jo: The Smart Journal

We introduce Jo, a mobile application that attempts to improve user's well-being. Jo is a journaling application--users log their important moments via short texts and optionally an attached photo. Unlike a static journal, Jo analyzes these moments and helps users take action towards increased well-being. For example, Jo annotates each moment with a set of values (e.g., family, socialization, mindfulness), thereby giving the user insights about the balance in their lives. In addition, Jo helps the user create reminders that enable them to create additional happy moments. We describe the results of fielding Jo in a study of 39 participants. The results illustrate the promise of a journaling application that provides personalized feedback, and points at further research.

cs.HC↗

arXiv2019

Adversarial Imitation Learning from Incomplete Demonstrations

Imitation learning targets deriving a mapping from states to actions, a.k.a. policy, from expert demonstrations. Existing methods for imitation learning typically require any actions in the demonstrations to be fully available, which is hard to ensure in real applications. Though algorithms for learning with unobservable actions have been proposed, they focus solely on state information and overlook the fact that the action sequence could still be partially available and provide useful information for policy deriving. In this paper, we propose a novel algorithm called Action-Guided Adversarial Imitation Learning (AGAIL) that learns a policy from demonstrations with incomplete action sequences, i.e., incomplete demonstrations. The core idea of AGAIL is to separate demonstrations into state and action trajectories, and train a policy with state trajectories while using actions as auxiliary information to guide the training whenever applicable. Built upon the Generative Adversarial Imitation Learning, AGAIL has three components: a generator, a discriminator, and a guide. The generator learns a policy with rewards provided by the discriminator, which tries to distinguish state distributions between demonstrations and samples generated by the policy. The guide provides additional rewards to the generator when demonstrated actions for specific states are available. We compare AGAIL to other methods on benchmark tasks and show that AGAIL consistently delivers comparable performance to the state-of-the-art methods even when the action sequence in demonstrations is only partially available.

cs.LG↗

arXiv2019

Estimating Emotional Intensity from Body Poses for Human-Robot Interaction

Equipping social and service robots with the ability to perceive human emotional intensities during an interaction is in increasing demand. Most of existing work focuses on determining which emotion(s) participants are expressing from facial expressions but largely overlooks the emotional intensities spontaneously revealed by other social cues, especially body languages. In this paper, we present a real-time method for robots to capture fluctuations of participants' emotional intensities from their body poses. Unlike conventional joint-position-based approaches, our method adopts local joint transformations as pose descriptors which are invariant to subject body differences as well as the pose sensor positions. In addition, we use a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) architecture to take the specific emotion context into account when estimating emotional intensities from body poses. The dataset evaluation suggests that the proposed method is effective and performs better than baseline method on the test dataset. Also, a series of succeeding field tests on a physical robot demonstrates that the proposed method effectively estimates subjects emotional intensities in real-time. Furthermore, the robot equipped with our method is perceived to be more emotion-sensitive and more emotionally intelligent.

cs.HC↗

arXiv2018

Manifest the Invisible: Design for Situational Awareness of Physical Environments in Virtual Reality

Virtual Reality (VR) provides immersive experiences in the virtual world, but it may reduce users' awareness of physical surroundings and cause safety concerns and psychological discomfort. Hence, there is a need of an ambient information design to increase users' situational awareness (SA) of physical elements when they are immersed in VR environment. This is challenging, since there is a tradeoff between the awareness in reality and the interference with users' experience in virtuality. In this paper, we design five representations (indexical, symbolic, and iconic with three emotions) based on two dimensions (vividness and emotion) to address the problem. We conduct an empirical study to evaluate participants' SA, perceived breaks in presence (BIPs), and perceived engagement through VR tasks that require movement in space. Results show that designs with higher vividness evoke more SA, designs that are more consistent with the virtual environment can mitigate the BIP issue, and emotion-evoking designs are more engaging.

cs.HC↗

arXiv2018

WeSeer: Visual Analysis for Better Information Cascade Prediction of WeChat Articles

Social media, such as Facebook and WeChat, empowers millions of users to create, consume, and disseminate online information on an unprecedented scale. The abundant information on social media intensifies the competition of WeChat Public Official Articles (i.e., posts) for gaining user attention due to the zero-sum nature of attention. Therefore, only a small portion of information tends to become extremely popular while the rest remains unnoticed or quickly disappears. Such a typical `long-tail' phenomenon is very common in social media. Thus, recent years have witnessed a growing interest in predicting the future trend in the popularity of social media posts and understanding the factors that influence the popularity of the posts. Nevertheless, existing predictive models either rely on cumbersome feature engineering or sophisticated parameter tuning, which are difficult to understand and improve. In this paper, we study and enhance a point process-based model by incorporating visual reasoning to support communication between the users and the predictive model for a better prediction result. The proposed system supports users to uncover the working mechanism behind the model and improve the prediction accuracy accordingly based on the insights gained. We use realistic WeChat articles to demonstrate the effectiveness of the system and verify the improved model on a large scale of WeChat articles. We also elicit and summarize the feedback from WeChat domain experts.

cs.HC↗