Who am I?

I am a postdoctoral researcher at the Ubiquitous Interaction Research Group, Department of Computer Science, University of Helsinki, where I received my Ph.D. I received a Master of Science in System Information Sciences from Tohoku University, Japan, and a Bachelor of Engineering in Digital Media Technology from Zhejiang University, China.

My research interests include Information Visualization, Human-Computer Interaction, and Human-Centered AI.

Here are several projects I did.

VMS (Visualization for Model Sensemaking and Selection) enables users of the model to evaluate and choose predictive models based on model performance ranking, pairwise model comparison of individual prediction cases, and global & local feature importance. Users can also filter cases of interest through data attributes. Prototype Article

The improved version of MediSyn synthesizes five drug-target datasets. We also redesigned the interaction of MediSyn based on the notion of entities (that is, taking drugs and targets as entities) for insight generation. MediSyn supports five types of interactions: 1) selecting entities of interest, 2) connecting relevant entities, 3) elaborating by retrieving the details of entity relations, 4) exploring other entities, and 5) entity-based insight sharing. Source code Article

MediSyn: Uncertainty-aware visualization of multiple biomedical datasets to support drug treatment selection

The first version of MediSyn synthesizes two drug-target datasets. It uses a matrix-based layout to visually link drugs, targets (i.e., mutations), and tumor types. Data uncertainties are salient in MediSyn as (i) missing data are exposed through the matrix view; (ii) inconsistencies between datasets are shown via overlaid layers; and (iii) data credibility is conveyed through links to data provenance. Article

Tuple retriveal

Tuple retrieval visualizes search results under various combinations of search terms. It also suggests relevant terms and combinations of terms to help navigate the search space.

Scalable exploration of relevance prospects to support decision making

IntersectionExplorer applied the design of UpSet to inter-relate publications generated by recommendation agents and other users (such as bookmarks) with the idea that the item suggested by multiple sources can increase the likelihood of user adoption of it. Source code Article

There are a series of extensions I made for the dynamic and flexible interactive photoshow (D-Flip) as my master's research project. The extension includes adapting the system to various types of content, such as paintings and flashcards, and various interaction modalities, such as multi-touch public displays and whole-body interactions. More videos

Selected publications

Chen He, Vishnu Raj, Hans Moen, Tommi Gröhn, Chen Wang, Laura-Maria Peltonen, Saila Koivusalo, Pekka Marttinen, and Giulio Jacucci, 2024, VMS: Interactive visualization to support the sensemaking and selection of predictive models., in Proceedings of the 29th International Conference on Intelligent User Interfaces (IUI '24), ACM, 229–244. [Video] [Open access]

Chen He, Luana Micallef, Baris Serim, Tung Vuong, Tuukka Ruotsalo, and Giulio Jacucci, Interactive visual facets to support fluid exploratory search, Journal of Visualization, Vol. 26, pp. 211-230, February 2023. [Video] [Open access]

Chen He, Entity-based insight discovery in visual data exploration, Ph.D. dissertation, 27 Jan 2022. [Open access]

Chen He, Luana Micallef, Liye He, Gopal Peddinti, Tero Aittokallio, and Giulio Jacucci, Characterizing the quality of insight by interactions: A case study, IEEE Transactions on Visualization and Computer Graphics, Vol. 27, No. 8, pp. 3410-3424, 1 August 2021. [DOI]

Chen He, Luana Micallef, Zia-ur-Rehman Tanol, Samuel Kaski, Tero Aittokallio, and Giulio Jacucci, MediSyn: Uncertainty-aware visualization of multiple biomedical datasets to support drug treatment selection, BMC bioinformatics, 18, No. 10, 393, 2017. [Open access]

Chen He, Denis Parra, and Katrien Verbert, Interactive recommender systems: A survey of the state of the art and future research challenges and opportunities, Expert Systems with Applications, Vol. 56, pp. 9-27, ISSN 0957-4174, 1 September 2016. [DOI]

Teaching

I teach the Interaction Data Visualization course at the University of Helsinki as part of the Master's Program in Data science and Computer Science. Check out the lecture slides below.

As an introduction to data visualization, this presentation introduces the definition and purposes of data visualization and covers common techniques of visualizing multi-dimensional, graph, and set-typed data.

Topics include optical illusions, visual processing model, preattentive processing, Gestalt laws, etc.

This lecture is about the LATCH principle for data organization and Tufte design principles.

This lecture presents the nested model for visualization design proposed by Tamara Munzner and two case studies.

This lecture explores techniques of visualizing one, two, and multi-dimensional data, as well as the use of composite views for multi-dimensional data representation.

This lecture addresses techniques to visualize graphs (e.g., node-link diagrams and adjacency matrix) and trees (e.g., space-filling techniques).

This lecture discusses techniques to visualize set-typed data, such as Venn and Euler diagrams.

This lecture covers seven categories of interactions in visualization (Yi et al., 2007), as well as methods of interacting with focused and contextual views (Cockburn et al., 2009).

This lecture discusses quantitative and qualitative evaluation methods in visualization.

This lecture examines the concepts of human-centered AI and the role of visualization involved.