Congratulations to Crowd Lab Ph.D. student Sukrit Venkatagiri on his selection as one of 12 Graduate Student Fellows of the Rita Allen Foundation’s Misinformation Solutions Forum, which took place in October 2018 in Washington, DC. As a Graduate Fellow, Sukrit received a travel grant to attend the Forum and co-authored (with Amy Zhang of MIT) an essay that was published in the Forum’s proceedings.
Maoyuan Sun, assistant professor of computer and information science at UMass-Dartmouth, recently published an article, titled, “The Effect of Edge Bundling and Seriation on Sensemaking of Biclusters in Bipartite Graphs,” in the journal IEEE Transactions on Visualization and Computer Graphics (TVCG). The co-authors are Jian Zhao, Hao Wu, Dr. Luther, Chris North, and Naren Ramakrishnan. The article’s abstract is as follows:
Exploring coordinated relationships (e.g., shared relationships between two sets of entities) is an important analytics task in a variety of real-world applications, such as discovering similarly behaved genes in bioinformatics, detecting malware collusions in cyber security, and identifying products bundles in marketing analysis. Coordinated relationships can be formalized as biclusters. In order to support visual exploration of biclusters, bipartite graphs based visualizations have been proposed, and edge bundling is used to show biclusters. However, it suffers from edge crossings due to possible overlaps of biclusters, and lacks in-depth understanding of its impact on user exploring biclusters in bipartite graphs. To address these, we propose a novel bicluster-based seriation technique that can reduce edge crossings in bipartite graphs drawing and conducted a user experiment to study the effect of edge bundling and this proposed technique on visualizing biclusters in bipartite graphs. We found that they both had impact on reducing entity visits for users exploring biclusters, and edge bundles helped them find more justified answers. Moreover, we identified four key trade-offs that inform the design of future bicluster visualizations. The study results suggest that edge bundling is critical for exploring biclusters in bipartite graphs, which helps to reduce low-level perceptual problems and support high-level inferences.
Our paper on geolocating images using crowdsourcing and diagramming was accepted for the International Joint Conference on Artificial Intelligence (IJCAI 2018) in Stockholm, Sweden. Dr. Luther will give the presentation. Congratulations to co-authors and Crowd Lab alumni Rachel Kohler and John Purviance!
Our paper, Crowdsourcing Intelligence Analysis with Context Slices, was accepted to the CHI 2018 Sensemaking in a Senseless World workshop in the most competitive long presentation category (21% acceptance rate). Congratulations to Crowd Lab co-authors Tianyi Li (Ph.D. student) and Asmita Shah (undergraduate researcher), as well as Tianyi’s co-advisor, Dr. Chris North.
Dr. Luther gave the presentation at the conference in Montreal, Canada, in April.
Our full paper on CrowdLayout, a system that uses crowdsourcing to design better layouts of biological network visualizations, was accepted for the CHI 2018 conference in Montreal, Canada. The acceptance rate for this top-tier HCI conference was 26% (of 2,590 submissions). Congrats to Crowd Lab alumni Divit Singh and Lee Lisle, and collaborator Dr. T.M. Murali, on this accomplishment.
Our paper on crowdsourced image geolocation and diagramming won the Notable Paper Award at HCOMP 2017. Congrats to Crowd Lab alums Rachel Kohler and John Purviance, co-authors of the paper, for this recognition. In the photo above, Dr. Luther receives the award certificate on behalf of his co-authors from Adam Kalai and Steven Dow (HCOMP 2017 co-chairs) and Jeff Nichols (Awards committee).
You can read the award-winning paper, Supporting Image Geolocation with Diagramming and Crowdsourcing, in the online proceedings.
Our work on GraphSpace, an online hub where scientists can share network data, was published in Bioinformatics journal. The title of the article is, GraphSpace: stimulating interdisciplinary collaborations in network biology. The authors include Dr. Luther, his collaborator Dr. T.M. Murali, and Crowd Lab alum Divit Singh.
Here’s the abstract for the article:
Networks have become ubiquitous in systems biology. Visualization is a crucial component in their analysis. However, collaborations within research teams in network biology are hampered by software systems that are either specific to a computational algorithm, create visualizations that are not biologically meaningful, or have limited features for sharing networks and visualizations. We present GraphSpace, a web-based platform that fosters team science by allowing collaborating research groups to easily store, interact with, layout and share networks.
This work was partly funded by our NIH Big Data to Knowledge grant.
Our paper on GroundTruth, a system that allows experts to collaborate with crowds on image geolocation tasks, was accepted for the second GroupSight workshop at HCOMP 2017. Congratulations to Crowd Lab alumni Rachel Kohler and John Purviance, co-authors on the accepted paper.
Here’s the abstract for the paper:
Geolocation, the process of identifying the specific location where a photo or video was taken, is an important task in verifying evidence for investigations in journalism, national security, human rights, and other domains. However, experts typically perform geolocation work as a time-consuming, manual process. This paper introduces GroundTruth, a web-based system that leverages the powerful vision system of crowd workers to support experts in image geolocation tasks. We describe the technical contributions of GroundTruth and present preliminary results from an evaluation with expert geolocators and novice crowds.
Our full paper on using crowdsourcing and diagramming to support image and video geolocation was accepted for the HCOMP 2017 conference in Québec City, Canada. Only 29% of paper submissions were accepted for this competitive crowdsourcing conference. Congrats to MS Computer Science alumna Rachel Kohler and BS Computer Science alumnus John Purviance, the first and second authors of the paper, respectively.
Here’s the abstract for the paper:
Geolocation, the process of identifying the precise location in the world where a photo or video was taken, is central to many types of investigative work, from debunking fake news posted on social media to locating terrorist training camps. Professional geolocation is often a manual, time-consuming process that involves searching large areas of satellite imagery for potential matches. In this paper, we explore how crowdsourcing can be used to support expert image geolocation. We adapt an expert diagramming technique to overcome spatial reasoning limitations of novice crowds, allowing them to support an expert’s search. In two experiments (n=1080), we found that diagrams work significantly better than ground-level photos and allow crowds to reduce a search area by half before any expert intervention. We also discuss hybrid approaches to complex image analysis combining crowds, experts, and computer vision.
The full version of the paper can be read here.