Research Projects
Human-centric & Data-driven
My research focuses on visual analytics and knowledge discovery of complex datasets. Specifically, I extract insights from complex and unstructured data, such as scientific literature, social science survey data, and knowledge graphs of food area. These datasets originate from diverse domains, but they are all multidimensional, multirelational, and contain many entities with rich semantics. Over the past five years, I have played a major role in many research projects funded by NSF and developed many innovative ideas in interactive data query, knowledge discovery, and visual analytics to support human-centric, data-driven decision making. My research was published in the very top journal in data visualization, IEEE Transactions on Visualization and Computer Graphics.
KeywordMap: Attention-based Visual Exploration for Keyword Analysis
Built a word network using attentions.
Proposed a novel algorithm to compute the influence of each word
Developed an interactive visual analytics system to support multi-level analysis of keywords
PhraseMap: Keyphrases Recommendation for Information-Seeking
Built an attention-based PhraseMap
Proposed a novel grid-based visualization design
Designed a navigation algorithm: including (1) a question-answering (QA) model (2) updating relevant phrases based on users’ feedback.
DocFlow: A Visual Analytics System for Question-Based Document Retrieval and Categorization
Trained a Dual-BioBERT model to identify relevant documents from Natural Languages.
Utilized BioBERT-QA model to perform answer extraction to categorize documents.
Built a data-flow system to flexible build different analysis pipelines.
KG-PRE-view: Democratizing A TVCG Knowledge Graph through Visual Explorations
An Interactive Knowledge and Learning Environment in Smart Foodsheds Paper
Proposed an interactive knowledge and learning environment (IKLE) that integrates three programming and modeling languages to support downstream tasks in the analysis pipeline.
Developed algorithms to automate the generation of each language.
Designed and developed a dataflow visualization system, which embeds the automatic language generations into components and allows users to build their analysis pipeline by dragging and connecting components of interest.
Proposed a Semantic Knowledge Graph (SKG) that integrates semantic concepts from abstracts and other meta-information to represent the corpus.
Developed a Knowledge Extraction Module that includes a semi-supervised pipeline for entity extraction and entity normalization.
Designed and developed a dataflow system that demonstrates how to conduct various semantic queries flexibly and interactively over the SKG.
Enabled seamless exploration of graph data through a dynamic and engaging interface.
Integrated Graph View, Table View, and Map View for comprehensive multi-perspective analysis.
Utilized Tapis Pods Service for efficient and scalable deployment.