Conglei Shi

TextFlow: Towards Better Understanding of Evolving Topics in Text

Understanding how topics evolve in text data is an important and challenging task. Although much work has been devoted to topic analysis, the study of topic evolution has largely been limited to individual topics. In this paper, we introduce TextFlow, a seamless integration of visualization and topic mining techniques, for analyzing various evolution patterns that emerge from multiple topics. We first extend an existing analysis technique to extract three-level features: the topic evolution trend, the critical event, and the keyword correlation. Then a coherent visualization that consists of three new visual components is designed to convey complex relationships between them. Through interaction, the topic mining model and visualization can communicate with each other to help users refine the analysis result and gain insights into the data progressively. Finally, two case studies are conducted to demonstrate the effectiveness and usefulness of TextFlow in helping users understand the major topic evolution patterns in time-varying text data.

RankExplorer: Visualization of Ranking Changes in Large Time Series Data

For many applications involving time series data, people are often interested in the changes of item values over time as well as their ranking changes. For example, people search many words via search engines like Google and Bing every day. Analysts are interested in both the absolute searching number for each word as well as their relative rankings. Both sets of statistics may change over time. For very large time series data with thousands of items, how to visually present ranking changes is an interesting challenge. In this paper, we propose RankExplorer, a novel visualization method based on ThemeRiver to reveal the ranking changes. Our method consists of four major components: 1) a segmentation method which partitions a large set of time series curves into a manageable number of ranking categories; 2) an extended ThemeRiver view with embedded color bars and changing glyphs to show the evolution of aggregation values related to each ranking category over time as well as the content changes in each ranking category; 3) a trend curve to show the degree of ranking changes over time; 4) rich user interactions to support interactive exploration of ranking changes. We have applied our method to some real time series data and the case studies demonstrate that our method can reveal the underlying patterns related to ranking changes which might otherwise be obscured in traditional visualizations.

Time Curves: Folding Time to Visualize Patterns of Temporal Evolution in Data

We introduce time curves as a general approach for visualizing patterns of evolution in temporal data. Examples of such patterns include slow and regular progressions, large sudden changes, and reversals to previous states. These patterns can be of interest in a range of domains, such as collaborative document editing, dynamic network analysis, and video analysis. Time curves employ the metaphor of folding a timeline visualization into itself so as to bring similar time points close to each other. This metaphor can be applied to any dataset where a similarity metric between temporal snapshots can be defined, thus it is largely datatype-agnostic. We illustrate how time curves can visually reveal informative patterns in a range of different datasets.

TargetVue: Visual Analysis of Anomalous User Behaviors in Online Communication Systems

Users with anomalous behaviors in online communication systems (e.g. email and social medial platforms) are potential threats to society. Automated anomaly detection based on advanced machine learning techniques has been developed to combat this issue; challenges remain, though, due to the difficulty of obtaining proper ground truth for model training and evaluation. Therefore, substantial human judgment on the automated analysis results is often required to better adjust the performance of anomaly detection. Unfortunately, techniques that allow users to understand the analysis results more efficiently, to make a confident judgment about anomalies, and to explore data in their context, are still lacking. In this paper, we propose a novel visual analysis system, TargetVue, which detects anomalous users via an unsupervised learning model and visualizes the behaviors of suspicious users in behavior-rich context through novel visualization designs and multiple coordinated contextual views. Particularly, TargetVue incorporates three new ego-centric glyphs to visually summarize a users behaviors which effectively present the users communication activities, features, and social interactions. An efficient layout method is proposed to place these glyphs on a triangle grid, which captures similarities among users and facilitates comparisons of behaviors of different users. We demonstrate the power of TargetVue through its application in a social bot detection challenge using Twitter data, a case study based on email records, and an interview with expert users. Our evaluation shows that TargetVue is beneficial to the detection of users with anomalous communication behaviors.

VisMOOC: Visualizing video clickstream data from massive open online courses

Massive Open Online Courses (MOOCs) platforms are becoming increasingly popular in recent years. With thousands of students watching course videos, enormous amounts of clickstream data are produced and recorded by the MOOCs platforms for each course. Such large-scale data provide a great opportunity for instructors and educational analysts to gain insight into online learning behaviors on an unprecedented scale. Nevertheless, the growing scale and unique characteristics of the data also pose a special challenge for effective data analysis. In this paper, we introduce VisMOOC, a visual analytic system to help analyze user learning behaviors by using video clickstream data from MOOC platforms. We work closely with the instructors of two Coursera courses to understand the data and collect task analysis requirements. A complete user-centered design process is further employed to design and develop VisMOOC. It includes three main linked views: the List View to show an overview of the clickstream differences among course videos, the Content-based View to show temporal variations in the total number of each type of click action along the video timeline, the Dashboard View to show various statistical information such as demographic information and temporal information. We conduct two case studies with the instructors to demonstrate the usefulness of VisMOOC and discuss new findings on learning behaviors.

LoyalTracker: Visualizing Loyalty Dynamics in Search Engines

The huge amount of user log data collected by search engine providers creates new opportunities to understand user loyalty and defection behavior at an unprecedented scale. However, this also poses a great challenge to analyze the behavior and glean insights into the complex, large data. In this paper, we introduce LoyalTracker, a visual analytics system to track user loyalty and switching behavior towards multiple search engines from the vast amount of user log data. We propose a new interactive visualization technique (flow view) based on a flow metaphor, which conveys a proper visual summary of the dynamics of user loyalty of thousands of users over time. Two other visualization techniques, a density map and a word cloud, are integrated to enable analysts to gain further insights into the patterns identified by the flow view. Case studies and the interview with domain experts are conducted to demonstrate the usefulness of our technique in understanding user loyalty and switching behavior in search engines.

PeakVizor: Visual Analytics of Peaks in Video Clickstreams from Massive Open Online Courses.

Massive open online courses (MOOCs) aim to facilitate open-access and massive-participation education. These courses have attracted millions of learners recently. At present, most MOOC platforms record the Web log data of learner interactions with course videos. Such large amounts of multivariate data pose a new challenge in terms of analyzing online learning behaviors. Previous studies have mainly focused on the aggregate behaviors of learners from a summative view; however, few attempts have been made to conduct a detailed analysis of such behaviors. To determine complex learning patterns in MOOC video interactions, this paper introduces a comprehensive visualization system called PeakVizor. This system enables course instructors and education experts to analyze the “peaks” or the video segments that generate numerous clickstreams. The system features three views at different levels: the overview with glyphs to display valuable statistics regarding the peaks detected; the flow view to present spatio-temporal information regarding the peaks; and the correlation view to show the correlation between different learner groups and the peaks. Case studies and interviews conducted with domain experts have demonstrated the usefulness and effectiveness of PeakVizor, and new findings about learning behaviors in MOOC platforms have been reported.

Visual analysis of set relations in a graph

Many applications can be modeled as a graph with additional attributes attached to the nodes. For example, a graph can be used to model the relationship of people in a social media website or a bibliographical dataset. Meanwhile, additional information is often available, such as the topics people are interested in and the music they listen to. Based on this additional information, different set relationships may exist among people. Revealing the set relationships in a network can help people gain social insight and better understand their roles within a community. In this paper, we present a visualization system for exploring set relations in a graph. Our system is designed to reveal three different relationships simultaneously: the social relationship of people, the set relationship among peoples items of interest, and the similarity relationship of the items. We propose two novel visualization designs: a) a glyph‐based visualization to reveal peoples set relationships in the context of their social networks; b) an integration of visual links and a contour map to show people and their items of interest which are clustered into different groups. The effectiveness of the designs has been demonstrated by the case studies on two representative datasets including one from a social music service website and another from an academic collaboration network.

PieceStack: Toward Better Understanding of Stacked Graphs

Stacked graphs have been widely adopted in various fields, because they are capable of hierarchically visualizing a set of temporal sequences as well as their aggregation. However, because of visual illusion issues, connections between overly-detailed individual layers and overly-generalized aggregation are intercepted. Consequently, information in this area has yet to be fully excavated. Thus, we present PieceStack in this paper, to reveal the relevance of stacked graphs in understanding intrinsic details of their displayed shapes. This new visual analytic design interprets the ways through which aggregations are generated with individual layers by interactively splitting and re-constructing the stacked graphs. A clustering algorithm is designed to partition stacked graphs into sub-aggregated pieces based on trend similarities of layers. We then visualize the pieces with augmented encoding to help analysts decompose and explore the graphs with respect to their interests. Case studies and a user study are conducted to demonstrate the usefulness of our technique in understanding the formation of stacked graphs.

Is the Whole Greater Than the Sum of Its Parts

The PART-WHOLE relationship routinely finds itself in many disciplines, ranging from collaborative teams, crowdsourcing, autonomous systems to networked systems. From the algorithmic perspective, the existing work has primarily focused on predicting the outcomes of the whole and parts, by either separate models or linear joint models, which assume the outcome of the parts has a linear and independent effect on the outcome of the whole. In this paper, we propose a joint predictive method named PAROLE to simultaneously and mutually predict the part and whole outcomes. The proposed method offers two distinct advantages over the existing work. First (Model Generality), we formulate joint PART-WHOLE outcome prediction as a generic optimization problem, which is able to encode a variety of complex relationships between the outcome of the whole and parts, beyond the linear independence assumption. Second (Algorithm Efficacy), we propose an effective and efficient block coordinate descent algorithm, which is able to find the coordinate-wise optimum with a linear complexity in both time and space. Extensive empirical evaluations on real-world datasets demonstrate that the proposed PAROLE (1) leads to consistent prediction performance improvement by modeling the non-linear part-whole relationship as well as part-part interdependency, and (2) scales linearly in terms of the size of the training dataset.