Xiaojuan Ma

Baiqiao Zhang, Xiangxian Li, Chao Zhou et al.

The low-intrusion and automated personality assessment is receiving increasing attention in psychology and human-computer interaction fields. This study explores an interactive approach for personality assessment, focusing on the multiplicity of personality representation. We propose a framework of Gamified Personality Assessment through Multi-Personality Representations (Multi-PR GPA). The framework leverages Large Language Models to empower virtual agents with different personalities. These agents elicit multifaceted human personality representations through engaging in interactive games. Drawing upon the multi-type textual data generated throughout the interaction, it achieves personality assessments with interpretable insights. Grounded in the classic Big Five personality theory, we developed a prototype system and conducted a user study to evaluate the efficacy of Multi-PR GPA. The results affirm the effectiveness of our approach in personality assessment and demonstrate its superior performance when considering the multiplicity of personality representation. Error structure analysis further revealed systematic assessment biases in LLMs, which multi-context aggregation partially mitigated.

Chengbo Zheng, Yuheng Wu, Chuhan Shi et al.

Existing research on human-AI collaborative decision-making focuses mainly on the interaction between AI and individual decision-makers. There is a limited understanding of how AI may perform in group decision-making. This paper presents a wizard-of-oz study in which two participants and an AI form a committee to rank three English essays. One novelty of our study is that we adopt a speculative design by endowing AI equal power to humans in group decision-making.We enable the AI to discuss and vote equally with other human members. We find that although the voice of AI is considered valuable, AI still plays a secondary role in the group because it cannot fully follow the dynamics of the discussion and make progressive contributions. Moreover, the divergent opinions of our participants regarding an "equal AI" shed light on the possible future of human-AI relations.

Shuai Ma, Qiaoyi Chen, Xinru Wang et al.

In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in communicating the nuances of conflicting opinions to the AI when disagreements occur. To tackle this challenge, we propose Human-AI Deliberation, a novel framework to promote human reflection and discussion on conflicting human-AI opinions in decision-making. Based on theories in human deliberation, this framework engages humans and AI in dimension-level opinion elicitation, deliberative discussion, and decision updates. To empower AI with deliberative capabilities, we designed Deliberative AI, which leverages large language models (LLMs) as a bridge between humans and domain-specific models to enable flexible conversational interactions and faithful information provision. An exploratory evaluation on a graduate admissions task shows that Deliberative AI outperforms conventional explainable AI (XAI) assistants in improving humans' appropriate reliance and task performance. Based on a mixed-methods analysis of participant behavior, perception, user experience, and open-ended feedback, we draw implications for future AI-assisted decision tool design.

Dong Qiao, Xinxian Ma, Jicong Fan

High-dimensional data visualization is crucial in the big data era and these techniques such as t-SNE and UMAP have been widely used in science and engineering. Big data, however, is often distributed across multiple data centers and subject to security and privacy concerns, which leads to difficulties for the standard algorithms of t-SNE and UMAP. To tackle the challenge, this work proposes Fed-tSNE and Fed-UMAP, which provide high-dimensional data visualization under the framework of federated learning, without exchanging data across clients or sending data to the central server. The main idea of Fed-tSNE and Fed-UMAP is implicitly learning the distribution information of data in a manner of federated learning and then estimating the global distance matrix for t-SNE and UMAP. To further enhance the protection of data privacy, we propose Fed-tSNE+ and Fed-UMAP+. We also extend our idea to federated spectral clustering, yielding algorithms of clustering distributed data. In addition to these new algorithms, we offer theoretical guarantees of optimization convergence, distance and similarity estimation, and differential privacy. Experiments on multiple datasets demonstrate that, compared to the original algorithms, the accuracy drops of our federated algorithms are tiny.

Quyet V. Do, Junze Li, Tung-Duong Vuong et al.

Commonsense datasets have been well developed in Natural Language Processing, mainly through crowdsource human annotation. However, there are debates on the genuineness of commonsense reasoning benchmarks. In specific, a significant portion of instances in some commonsense benchmarks do not concern commonsense knowledge. That problem would undermine the measurement of the true commonsense reasoning ability of evaluated models. It is also suggested that the problem originated from a blurry concept of commonsense knowledge, as distinguished from other types of knowledge. To demystify all of the above claims, in this study, we survey existing definitions of commonsense knowledge, ground into the three frameworks for defining concepts, and consolidate them into a multi-framework unified definition of commonsense knowledge (so-called consolidated definition). We then use the consolidated definition for annotations and experiments on the CommonsenseQA and CommonsenseQA 2.0 datasets to examine the above claims. Our study shows that there exists a large portion of non-commonsense-knowledge instances in the two datasets, and a large performance gap on these two subsets where Large Language Models (LLMs) perform worse on commonsense-knowledge instances.

Hanfang Lyu, Yuanchen Bai, Xin Liang et al.

Preference-based learning aims to align robot task objectives with human values. One of the most common methods to infer human preferences is by pairwise comparisons of robot task trajectories. Traditional comparison-based preference labeling systems seldom support labelers to digest and identify critical differences between complex trajectories recorded in videos. Our formative study (N = 12) suggests that individuals may overlook non-salient task features and establish biased preference criteria during their preference elicitation process because of partial observations. In addition, they may experience mental fatigue when given many pairs to compare, causing their label quality to deteriorate. To mitigate these issues, we propose FARPLS, a Feature-Augmented Robot trajectory Preference Labeling System. FARPLS highlights potential outliers in a wide variety of task features that matter to humans and extracts the corresponding video keyframes for easy review and comparison. It also dynamically adjusts the labeling order according to users' familiarities, difficulties of the trajectory pair, and level of disagreements. At the same time, the system monitors labelers' consistency and provides feedback on labeling progress to keep labelers engaged. A between-subjects study (N = 42, 105 pairs of robot pick-and-place trajectories per person) shows that FARPLS can help users establish preference criteria more easily and notice more relevant details in the presented trajectories than the conventional interface. FARPLS also improves labeling consistency and engagement, mitigating challenges in preference elicitation without raising cognitive loads significantly

Shishi Xiao, Liangwei Wang, Xiaojuan Ma et al.

Semantic typographic logos harmoniously blend typeface and imagery to represent semantic concepts while maintaining legibility. Conventional methods using spatial composition and shape substitution are hindered by the conflicting requirement for achieving seamless spatial fusion between geometrically dissimilar typefaces and semantics. While recent advances made AI generation of semantic typography possible, the end-to-end approaches exclude designer involvement and disregard personalized design. This paper presents TypeDance, an AI-assisted tool incorporating design rationales with the generative model for personalized semantic typographic logo design. It leverages combinable design priors extracted from uploaded image exemplars and supports type-imagery mapping at various structural granularity, achieving diverse aesthetic designs with flexible control. Additionally, we instantiate a comprehensive design workflow in TypeDance, including ideation, selection, generation, evaluation, and iteration. A two-task user evaluation, including imitation and creation, confirmed the usability of TypeDance in design across different usage scenarios

Quan Li, Haipeng Zeng, Zhenhui Peng et al.

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.

Dakuo Wang, Xiaojuan Ma, April Yi Wang

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.

Qiangqiang Liu, Quan Li, Zhihua Zhu et al.

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.

Meng Xia, Reshika Palaniyappan Velumani, Yong Wang et al.

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.

Qiangqiang Liu, Quan Li, Chunfeng Tang et al.

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.

Mingfei Sun, Zhenhui Peng, Meng Xia et al.

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.

Mingfei Sun, Xiaojuan Ma

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.

Mingfei Sun, Yiqing Mou, Hongwen Xie et al.

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.

Quan Li, Kristanto Sean Njotoprawiro, Hammad Haleem et al.

Constructing latent vector representation for nodes in a network through embedding models has shown its practicality in many graph analysis applications, such as node classification, clustering, and link prediction. However, despite the high efficiency and accuracy of learning an embedding model, people have little clue of what information about the original network is preserved in the embedding vectors. The abstractness of low-dimensional vector representation, stochastic nature of the construction process, and non-transparent hyper-parameters all obscure understanding of network embedding results. Visualization techniques have been introduced to facilitate embedding vector inspection, usually by projecting the embedding space to a two-dimensional display. Although the existing visualization methods allow simple examination of the structure of embedding space, they cannot support in-depth exploration of the embedding vectors. In this paper, we design an exploratory visual analytics system that supports the comparative visual interpretation of embedding vectors at the cluster, instance, and structural levels. To be more specific, it facilitates comparison of what and how node metrics are preserved across different embedding models and investigation of relationships between node metrics and selected embedding vectors. Several case studies confirm the efficacy of our system. Experts' feedback suggests that our approach indeed helps them better embrace the understanding of network embedding models.

Quan Li, Ziming Wu, Lingling Yi et al.

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.

Hyojin Bahng, Seungjoo Yoo, Wonwoong Cho et al.

This paper proposes a novel approach to generate multiple color palettes that reflect the semantics of input text and then colorize a given grayscale image according to the generated color palette. In contrast to existing approaches, our model can understand rich text, whether it is a single word, a phrase, or a sentence, and generate multiple possible palettes from it. For this task, we introduce our manually curated dataset called Palette-and-Text (PAT). Our proposed model called Text2Colors consists of two conditional generative adversarial networks: the text-to-palette generation networks and the palette-based colorization networks. The former captures the semantics of the text input and produce relevant color palettes. The latter colorizes a grayscale image using the generated color palette. Our evaluation results show that people preferred our generated palettes over ground truth palettes and that our model can effectively reflect the given palette when colorizing an image.

Leye Wang, Xu Geng, Xiaojuan Ma et al.

Spatio-temporal prediction is a key type of tasks in urban computing, e.g., traffic flow and air quality. Adequate data is usually a prerequisite, especially when deep learning is adopted. However, the development levels of different cities are unbalanced, and still many cities suffer from data scarcity. To address the problem, we propose a novel cross-city transfer learning method for deep spatio-temporal prediction tasks, called RegionTrans. RegionTrans aims to effectively transfer knowledge from a data-rich source city to a data-scarce target city. More specifically, we first learn an inter-city region matching function to match each target city region to a similar source city region. A neural network is designed to effectively extract region-level representation for spatio-temporal prediction. Finally, an optimization algorithm is proposed to transfer learned features from the source city to the target city with the region matching function. Using citywide crowd flow prediction as a demonstration experiment, we verify the effectiveness of RegionTrans. Results show that RegionTrans can outperform the state-of-the-art fine-tuning deep spatio-temporal prediction models by reducing up to 10.7% prediction error.

Leye Wang, Gehua Qin, Dingqi Yang et al.

For real-world mobile applications such as location-based advertising and spatial crowdsourcing, a key to success is targeting mobile users that can maximally cover certain locations in a future period. To find an optimal group of users, existing methods often require information about users' mobility history, which may cause privacy breaches. In this paper, we propose a method to maximize mobile crowd's future location coverage under a guaranteed location privacy protection scheme. In our approach, users only need to upload one of their frequently visited locations, and more importantly, the uploaded location is obfuscated using a geographic differential privacy policy. We propose both analytic and practical solutions to this problem. Experiments on real user mobility datasets show that our method significantly outperforms the state-of-the-art geographic differential privacy methods by achieving a higher coverage under the same level of privacy protection.

Leye Wang, Xu Geng, Jintao Ke et al.

Ridesourcing platforms like Uber and Didi are getting more and more popular around the world. However, unauthorized ridesourcing activities taking advantages of the sharing economy can greatly impair the healthy development of this emerging industry. As the first step to regulate on-demand ride services and eliminate black market, we design a method to detect ridesourcing cars from a pool of cars based on their trajectories. Since licensed ridesourcing car traces are not openly available and may be completely missing in some cities due to legal issues, we turn to transferring knowledge from public transport open data, i.e, taxis and buses, to ridesourcing detection among ordinary vehicles. We propose a two-stage transfer learning framework. In Stage 1, we take taxi and bus data as input to learn a random forest (RF) classifier using trajectory features shared by taxis/buses and ridesourcing/other cars. Then, we use the RF to label all the candidate cars. In Stage 2, leveraging the subset of high confident labels from the previous stage as input, we further learn a convolutional neural network (CNN) classifier for ridesourcing detection, and iteratively refine RF and CNN, as well as the feature set, via a co-training process. Finally, we use the resulting ensemble of RF and CNN to identify the ridesourcing cars in the candidate pool. Experiments on real car, taxi and bus traces show that our transfer learning framework, with no need of a pre-labeled ridesourcing dataset, can achieve similar accuracy as the supervised learning methods.