arXiv subjects

Xingbo Wang

Publications and source records attributed to Xingbo Wang.

At least 37 records · Page 2Linked to original sources

arXiv2024

Trinity: Synchronizing Verbal, Nonverbal, and Visual Channels to Support Academic Oral Presentation Delivery

Academic Oral Presentation (AOP) allows English-As-Foreign-Language (EFL) students to express ideas, engage in academic discourse, and present research findings. However, while previous efforts focus on training efficiency or speech assistance, EFL students often face the challenge of seamlessly integrating verbal, nonverbal, and visual elements into their presentations to avoid coming across as monotonous and unappealing. Based on a need-finding survey, a design study, and an expert interview, we introduce Trinity, a hybrid mobile-centric delivery support system that provides guidance for multichannel delivery on-the-fly. On the desktop side, Trinity facilitates script refinement and offers customizable delivery support based on large language models (LLMs). Based on the desktop configuration, Trinity App enables a remote mobile visual control, multi-level speech pace modulation, and integrated delivery prompts for synchronized delivery. A controlled between-subject user study suggests that Trinity effectively supports AOP delivery and is perceived as significantly more helpful than baselines, without excessive cognitive load.

cs.HC↗

arXiv2024

From gymnastics to virtual nonholonomic constraints: energy injection, dissipation, and regulation for the acrobot

In this article we study virtual nonholonomic constraints, which are relations between the generalized coordinates and momenta of a mechanical system that can be enforced via feedback control. We design a constraint which emulates gymnastics giant motion in an acrobot, and prove that this constraint can inject or dissipate energy based on the sign of a design parameter. The proposed constraint is tested both in simulation and experimentally on a real-world acrobot, demonstrating highly effective energy regulation properties and robustness to a variety of disturbances.

cs.RO↗

arXiv2024

POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Models

Large language models (LLMs) have exhibited impressive abilities for multimodal content comprehension and reasoning with proper prompting in zero- or few-shot settings. Despite the proliferation of interactive systems developed to support prompt engineering for LLMs across various tasks, most have primarily focused on textual or visual inputs, thus neglecting the complex interplay between modalities within multimodal inputs. This oversight hinders the development of effective prompts that guide model multimodal reasoning processes by fully exploiting the rich context provided by multiple modalities. In this paper, we present POEM, a visual analytics system to facilitate efficient prompt engineering for enhancing the multimodal reasoning performance of LLMs. The system enables users to explore the interaction patterns across modalities at varying levels of detail for a comprehensive understanding of the multimodal knowledge elicited by various prompts. Through diverse recommendations of demonstration examples and instructional principles, POEM supports users in iteratively crafting and refining prompts to better align and enhance model knowledge with human insights. The effectiveness and efficiency of our system are validated through two case studies and interviews with experts.

cs.HC↗

arXiv2024

ComPeer: A Generative Conversational Agent for Proactive Peer Support

Conversational Agents (CAs) acting as peer supporters have been widely studied and demonstrated beneficial for people's mental health. However, previous peer support CAs either are user-initiated or follow predefined rules to initiate the conversations, which may discourage users to engage and build relationships with the CAs for long-term benefits. In this paper, we develop ComPeer, a generative CA that can proactively offer adaptive peer support to users. ComPeer leverages large language models to detect and reflect significant events in the dialogue, enabling it to strategically plan the timing and content of proactive care. In addition, ComPeer incorporates peer support strategies, conversation history, and its persona into the generative messages. Our one-week between-subjects study (N=24) demonstrates ComPeer's strength in providing peer support over time and boosting users' engagement compared to a baseline user-initiated CA.

cs.HC↗

arXiv2024

LessonPlanner: Assisting Novice Teachers to Prepare Pedagogy-Driven Lesson Plans with Large Language Models

Preparing a lesson plan, e.g., a detailed road map with strategies and materials for instructing a 90-minute class, is beneficial yet challenging for novice teachers. Large language models (LLMs) can ease this process by generating adaptive content for lesson plans, which would otherwise require teachers to create from scratch or search existing resources. In this work, we first conduct a formative study with six novice teachers to understand their needs for support of preparing lesson plans with LLMs. Then, we develop LessonPlanner that assists users to interactively construct lesson plans with adaptive LLM-generated content based on Gagne's nine events. Our within-subjects study (N=12) shows that compared to the baseline ChatGPT interface, LessonPlanner can significantly improve the quality of outcome lesson plans and ease users' workload in the preparation process. Our expert interviews (N=6) further demonstrate LessonPlanner's usefulness in suggesting effective teaching strategies and meaningful educational resources. We discuss concerns on and design considerations for supporting teaching activities with LLMs.

cs.HC↗

arXiv2024

CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels

Online learning is a rapidly growing industry. However, a major doubt about online learning is whether students are as engaged as they are in face-to-face classes. An engagement recognition system can notify the instructors about the students condition and improve the learning experience. Current challenges in engagement detection involve poor label quality, extreme data imbalance, and intra-class variety - the variety of behaviors at a certain engagement level. To address these problems, we present the CMOSE dataset, which contains a large number of data from different engagement levels and high-quality labels annotated according to psychological advice. We also propose a training mechanism MocoRank to handle the intra-class variety and the ordinal pattern of different degrees of engagement classes. MocoRank outperforms prior engagement detection frameworks, achieving a 1.32% increase in overall accuracy and 5.05% improvement in average accuracy. Further, we demonstrate the effectiveness of multi-modality in engagement detection by combining video features with speech and audio features. The data transferability experiments also state that the proposed CMOSE dataset provides superior label quality and behavior diversity.

cs.CV↗

arXiv2024

RetAssist: Facilitating Vocabulary Learners with Generative Images in Story Retelling Practices

Reading and repeatedly retelling a short story is a common and effective approach to learning the meanings and usages of target words. However, learners often struggle with comprehending, recalling, and retelling the story contexts of these target words. Inspired by the Cognitive Theory of Multimedia Learning, we propose a computational workflow to generate relevant images paired with stories. Based on the workflow, we work with learners and teachers to iteratively design an interactive vocabulary learning system named RetAssist. It can generate sentence-level images of a story to facilitate the understanding and recall of the target words in the story retelling practices. Our within-subjects study (N=24) shows that compared to a baseline system without generative images, RetAssist significantly improves learners' fluency in expressing with target words. Participants also feel that RetAssist eases their learning workload and is more useful. We discuss insights into leveraging text-to-image generative models to support learning tasks.

cs.HC↗

arXiv2023

PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation

Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts. However, developing effective prompts for desired images can be challenging due to the complexity and ambiguity of natural language. This research proposes PromptMagician, a visual analysis system that helps users explore the image results and refine the input prompts. The backbone of our system is a prompt recommendation model that takes user prompts as input, retrieves similar prompt-image pairs from DiffusionDB, and identifies special (important and relevant) prompt keywords. To facilitate interactive prompt refinement, PromptMagician introduces a multi-level visualization for the cross-modal embedding of the retrieved images and recommended keywords, and supports users in specifying multiple criteria for personalized exploration. Two usage scenarios, a user study, and expert interviews demonstrate the effectiveness and usability of our system, suggesting it facilitates prompt engineering and improves the creativity support of the generative text-to-image model.

cs.AI↗

arXiv2023

Storyfier: Exploring Vocabulary Learning Support with Text Generation Models

Vocabulary learning support tools have widely exploited existing materials, e.g., stories or video clips, as contexts to help users memorize each target word. However, these tools could not provide a coherent context for any target words of learners' interests, and they seldom help practice word usage. In this paper, we work with teachers and students to iteratively develop Storyfier, which leverages text generation models to enable learners to read a generated story that covers any target words, conduct a story cloze test, and use these words to write a new story with adaptive AI assistance. Our within-subjects study (N=28) shows that learners generally favor the generated stories for connecting target words and writing assistance for easing their learning workload. However, in the read-cloze-write learning sessions, participants using Storyfier perform worse in recalling and using target words than learning with a baseline tool without our AI features. We discuss insights into supporting learning tasks with generative models.

cs.HC↗

arXiv2023

LiveRetro: Visual Analytics for Strategic Retrospect in Livestream E-Commerce

Livestream e-commerce integrates live streaming and online shopping, allowing viewers to make purchases while watching. However, effective marketing strategies remain a challenge due to limited empirical research and subjective biases from the absence of quantitative data. Current tools fail to capture the interdependence between live performances and feedback. This study identified computational features, formulated design requirements, and developed LiveRetro, an interactive visual analytics system. It enables comprehensive retrospective analysis of livestream e-commerce for streamers, viewers, and merchandise. LiveRetro employs enhanced visualization and time-series forecasting models to align performance features and feedback, identifying influences at channel, merchandise, feature, and segment levels. Through case studies and expert interviews, the system provides deep insights into the relationship between live performance and streaming statistics, enabling efficient strategic analysis from multiple perspectives.

cs.HC↗

arXiv2023

VideoPro: A Visual Analytics Approach for Interactive Video Programming

Constructing supervised machine learning models for real-world video analysis require substantial labeled data, which is costly to acquire due to scarce domain expertise and laborious manual inspection. While data programming shows promise in generating labeled data at scale with user-defined labeling functions, the high dimensional and complex temporal information in videos poses additional challenges for effectively composing and evaluating labeling functions. In this paper, we propose VideoPro, a visual analytics approach to support flexible and scalable video data programming for model steering with reduced human effort. We first extract human-understandable events from videos using computer vision techniques and treat them as atomic components of labeling functions. We further propose a two-stage template mining algorithm that characterizes the sequential patterns of these events to serve as labeling function templates for efficient data labeling. The visual interface of VideoPro facilitates multifaceted exploration, examination, and application of the labeling templates, allowing for effective programming of video data at scale. Moreover, users can monitor the impact of programming on model performance and make informed adjustments during the iterative programming process. We demonstrate the efficiency and effectiveness of our approach with two case studies and expert interviews.

cs.CV↗

arXiv2023

CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models

Recently, large pretrained language models have achieved compelling performance on commonsense benchmarks. Nevertheless, it is unclear what commonsense knowledge the models learn and whether they solely exploit spurious patterns. Feature attributions are popular explainability techniques that identify important input concepts for model outputs. However, commonsense knowledge tends to be implicit and rarely explicitly presented in inputs. These methods cannot infer models' implicit reasoning over mentioned concepts. We present CommonsenseVIS, a visual explanatory system that utilizes external commonsense knowledge bases to contextualize model behavior for commonsense question-answering. Specifically, we extract relevant commonsense knowledge in inputs as references to align model behavior with human knowledge. Our system features multi-level visualization and interactive model probing and editing for different concepts and their underlying relations. Through a user study, we show that CommonsenseVIS helps NLP experts conduct a systematic and scalable visual analysis of models' relational reasoning over concepts in different situations.

cs.CL↗

arXiv2023

MultiViz: Towards Visualizing and Understanding Multimodal Models

The promise of multimodal models for real-world applications has inspired research in visualizing and understanding their internal mechanics with the end goal of empowering stakeholders to visualize model behavior, perform model debugging, and promote trust in machine learning models. However, modern multimodal models are typically black-box neural networks, which makes it challenging to understand their internal mechanics. How can we visualize the internal modeling of multimodal interactions in these models? Our paper aims to fill this gap by proposing MultiViz, a method for analyzing the behavior of multimodal models by scaffolding the problem of interpretability into 4 stages: (1) unimodal importance: how each modality contributes towards downstream modeling and prediction, (2) cross-modal interactions: how different modalities relate with each other, (3) multimodal representations: how unimodal and cross-modal interactions are represented in decision-level features, and (4) multimodal prediction: how decision-level features are composed to make a prediction. MultiViz is designed to operate on diverse modalities, models, tasks, and research areas. Through experiments on 8 trained models across 6 real-world tasks, we show that the complementary stages in MultiViz together enable users to (1) simulate model predictions, (2) assign interpretable concepts to features, (3) perform error analysis on model misclassifications, and (4) use insights from error analysis to debug models. MultiViz is publicly available, will be regularly updated with new interpretation tools and metrics, and welcomes inputs from the community.

cs.LG↗

arXiv2023

Anchorage: Visual Analysis of Satisfaction in Customer Service Videos via Anchor Events

Delivering customer services through video communications has brought new opportunities to analyze customer satisfaction for quality management. However, due to the lack of reliable self-reported responses, service providers are troubled by the inadequate estimation of customer services and the tedious investigation into multimodal video recordings. We introduce Anchorage, a visual analytics system to evaluate customer satisfaction by summarizing multimodal behavioral features in customer service videos and revealing abnormal operations in the service process. We leverage the semantically meaningful operations to introduce structured event understanding into videos which help service providers quickly navigate to events of their interest. Anchorage supports a comprehensive evaluation of customer satisfaction from the service and operation levels and efficient analysis of customer behavioral dynamics via multifaceted visualization views. We extensively evaluate Anchorage through a case study and a carefully-designed user study. The results demonstrate its effectiveness and usability in assessing customer satisfaction using customer service videos. We found that introducing event contexts in assessing customer satisfaction can enhance its performance without compromising annotation precision. Our approach can be adapted in situations where unlabelled and unstructured videos are collected along with sequential records.

cs.HC↗

arXiv2023

XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis

Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding the underlying generation process is challenging. Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries. We present XNLI, an explainable NLI system for visual data analysis. The system introduces a Provenance Generator to reveal the detailed process of visual transformations, a suite of interactive widgets to support error adjustments, and a Hint Generator to provide query revision hints based on the analysis of user queries and interactions. Two usage scenarios of XNLI and a user study verify the effectiveness and usability of the system. Results suggest that XNLI can significantly enhance task accuracy without interrupting the NLI-based analysis process.

cs.HC↗

arXiv2022

ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset

Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts -- unwanted biases in the benchmark datasets -- can damage the effectiveness of benchmark datasets in revealing models' real capabilities. Since shortcuts vary in coverage, productivity, and semantic meaning, it is challenging for NLU experts to systematically understand and avoid them when creating benchmark datasets. In this paper, we develop a visual analytics system, ShortcutLens, to help NLU experts explore shortcuts in NLU benchmark datasets. The system allows users to conduct multi-level exploration of shortcuts. Specifically, Statistics View helps users grasp the statistics such as coverage and productivity of shortcuts in the benchmark dataset. Template View employs hierarchical and interpretable templates to summarize different types of shortcuts. Instance View allows users to check the corresponding instances covered by the shortcuts. We conduct case studies and expert interviews to evaluate the effectiveness and usability of the system. The results demonstrate that ShortcutLens supports users in gaining a better understanding of benchmark dataset issues through shortcuts, inspiring them to create challenging and pertinent benchmark datasets.

cs.HC↗

arXiv2022

GestureLens: Visual Analysis of Gestures in Presentation Videos

Appropriate gestures can enhance message delivery and audience engagement in both daily communication and public presentations. In this paper, we contribute a visual analytic approach that assists professional public speaking coaches in improving their practice of gesture training through analyzing presentation videos. Manually checking and exploring gesture usage in the presentation videos is often tedious and time-consuming. There lacks an efficient method to help users conduct gesture exploration, which is challenging due to the intrinsically temporal evolution of gestures and their complex correlation to speech content. In this paper, we propose GestureLens, a visual analytics system to facilitate gesture-based and content-based exploration of gesture usage in presentation videos. Specifically, the exploration view enables users to obtain a quick overview of the spatial and temporal distributions of gestures. The dynamic hand movements are firstly aggregated through a heatmap in the gesture space for uncovering spatial patterns, and then decomposed into two mutually perpendicular timelines for revealing temporal patterns. The relation view allows users to explicitly explore the correlation between speech content and gestures by enabling linked analysis and intuitive glyph designs. The video view and dynamic view show the context and overall dynamic movement of the selected gestures, respectively. Two usage scenarios and expert interviews with professional presentation coaches demonstrate the effectiveness and usefulness of GestureLens in facilitating gesture exploration and analysis of presentation videos.

cs.HC↗

arXiv2022

Persua: A Visual Interactive System to Enhance the Persuasiveness of Arguments in Online Discussion

Persuading people to change their opinions is a common practice in online discussion forums on topics ranging from political campaigns to relationship consultation. Enhancing people's ability to write persuasive arguments could not only practice their critical thinking and reasoning but also contribute to the effectiveness and civility in online communication. It is, however, not an easy task in online discussion settings where written words are the primary communication channel. In this paper, we derived four design goals for a tool that helps users improve the persuasiveness of arguments in online discussions through a survey with 123 online forum users and interviews with five debating experts. To satisfy these design goals, we analyzed and built a labeled dataset of fine-grained persuasive strategies (i.e., logos, pathos, ethos, and evidence) in 164 arguments with high ratings on persuasiveness from ChangeMyView, a popular online discussion forum. We then designed an interactive visual system, Persua, which provides example-based guidance on persuasive strategies to enhance the persuasiveness of arguments. In particular, the system constructs portfolios of arguments based on different persuasive strategies applied to a given discussion topic. It then presents concrete examples based on the difference between the portfolios of user input and high-quality arguments in the dataset. A between-subjects study shows suggestive evidence that Persua encourages users to submit more times for feedback and helps users improve more on the persuasiveness of their arguments than a baseline system. Finally, a set of design considerations was summarized to guide future intelligent systems that improve the persuasiveness in text.

cs.HC↗