Sponsored by: ACM Chicago Chapter, ACM ChicagoCHI Chapter and Discovery Partners Institute
Supported by: ACM SIGCHI Development Fund Grant
Location: Discovery Partners Institute (DPI), Classroom A, 200 S Wacker Dr., 4th Floor, Chicago, IL, 60606
Time: 1:00 to 6:00 PM (in-person and online)
We attend in-person events but often forget who we met and where. We receive many contact requests in our online social networks like LinkedIn and Facebook from people we do not know. How can we make it easier for people to connect from offline to online?
In this workshop, we will discuss:
- cutting-edge research on connecting people through offline and online interactions and how technology facilitates these transitions
- strategies for incorporating diversity into the development of mobile social networking applications
- establish a multidisciplinary and diverse network in mobile social networking, involving experts from academia, industry, and Chicago’s inclusive populations across computer science, sociology, and human-computer interaction
Workshop Committee:
Alvin Chin, Discovery Partners Institute
Kevin Leicht, Discovery Partners Institute
Philip Yu, University of Illinois Chicago
Ali Tafti, University of Illinois Chicago
Diego Gomez-Zara, University of Notre Dame
Agenda:
12:30 – 1 PM Networking
1-1:05 PM Welcoming remarks from the Chairs of the workshop, ACM Chicago and ACM Chicago CHI Chapter
1:05-1:10 PM Welcoming remarks from R&D Director at DPI, Venkat Venkatakrishnan
1:10-1:30 PM 30 seconds intro from the participants (in-person and online)
1:30-2:15 PM Keynote on Finding Emergent Patterns of Behaviors in Dynamic Heterogeneous Social and Behavioral Data, Anura Jayasumana, ACM Distinguished Speaker, Colorado State University
2:15-2:30 PM Coffee break
2:30-3:00 PM Talk #1 Social Networks in Physical Space (Ciro Catutto, ISI Foundation, Italy)
3:00-3:30 PM Talk #2 Ephemeral Social Networking – Connecting from Offline to Online (Alvin Chin, DPI)
3:30-4:00 PM Talk #3 Unleashing the Metaverse: A Study of Collaborations in Virtual Reality (Diego Gomez-Zara, University of Notre Dame)
4:00-4:30 PM Interactive activity led by Diego Gomez-Zara
4:30-5:00 PM Discussion
5:00-5:05 PM Closing
5:05-5:15 PM Poster pitches
5:15 – 6:00 PM Networking and Poster Session (Click here for the list of posters.)
As part of the workshop, there will be a poster session and students are encouraged to submit a poster title and abstract (see attached flyer). If accepted, the student is expected to present the poster in the poster session at the workshop in person.
Confirmed Speakers:
Anura Jayasumana, Professor, Colorado State University and ACM Distinguished Speaker
Emergent Patterns in Social Networks
Abstract:
Detecting latent or emerging patterns in dynamic networks is crucial across multiple domains, including homeland security, consumer analytics, behavioral health, and social computing. However, dynamic network data presents unique challenges in collection, mining, analytics and processing. We will present INSiGHT (Investigative Search for Graph Trajectories), a comprehensive framework for detecting emergent patterns of behaviors in knowledge networks containing social and behavioral data, with a focus on detection of domestic radicalization. To account for recurring behavioral indicators and the recency of behaviors as the imminence of a threat, e.g., INSiGHT provides parameterized methods to score multiple occurrences of indicators and to dampen the significance of indicators over time. Recognizing that radicalization can occur within small groups or collective plots, INSiGHT employs a non-combinatorial neighborhood matching technique that enables analysts to identify clusters of individuals potentially engaged in conspiracies. Our approach combines advanced natural language processing (NLP) and supervised machine learning models to classify textual data for radicalization indicators. Additionally, we have developed PINGS (Procedures for Investigative Graph Search), a specialized graph database library tailored for investigative search in social network mining. Finally, we will explore the potential of emerging Graph Neural Networks (GNNs) and Graph Embedded Neural Networks (GENNs) to pave the way for more advanced analytical capabilities in dynamic network analysis.
Bio:
Anura P. Jayasumana is a Professor in Electrical & Computer Engineering at Colorado State University where he holds a joint appointment in Computer Science. He is the Director of the Information Science and Technology Center (ISTeC) at CSU, a university-wide organization for promoting research, teaching and service in information sciences and technologies. He received a Ph.D. and M.S. in Electrical Engineering from Michigan State University and B.Sc. in Electronic and Telecommunications Engineering with First Class Honors from University of Moratuwa, Sri Lanka. His current research interests include mining knowledge networks for radicalization detection, Internet of Things, machine learning techniques for graphs, and synthetic data generation for machine learning. His research has been funded by DARPA, NSF, DoJ/NIJ, and industry. He served as a Distinguished Lecturer of the IEEE Communications Society (2014-17), and is currently an ACM Distinguished Speaker. He has served extensively as a consultant to companies ranging from startups to Fortune 100.
Ciro Cattuto, Scientific Director, ISI Foundation
Social Networks in Physical Space
Abstract:
Digital technologies allow us to quantify many important human behaviors and have revolutionized how we think about human mobility, opening new avenues for research in computational social science, urban mobility, epidemiology, and public health. This talk will focus on human proximity networks measured using wearable proximity sensors. We will discuss the evolution and state of the art of measurement technology and the lessons learned from over a decade of data collection experiences in various real-world environments, including schools, hospitals, households, low-resource rural settings, and more. We will illustrate the complex features and emergent patterns of time-resolved proximity networks and discuss how ideas and methods from network science and machine learning can support their modeling in important application scenarios.
Bio:
Ciro Cattuto is the Scientific Director of ISI Foundation, a non-profit research institute based in Turin, Italy, focusing on data science, complex systems, and their applications to public health and social impact. He holds a Ph.D. in Physics from the University of Perugia, Italy, and has worked as a research scientist at the University of Michigan in the USA, at the Enrico Fermi Center in Rome, and the Frontier Research System of RIKEN in Japan. He is a former Associate Professor in the Computer Science Department of the University of Torino, a former Expert in the Italian Department of Digital Transformation, and he served in the COVID-19 task force of the Italian Ministry of Innovation. He was a steering board member of CRT Foundation, a leading Italian philanthropy, and he is a member of the board of directors of OGR Torino. He is a founder and principal investigator of the SocioPatterns project, an international collaboration on measuring and modeling human proximity networks.
Alvin Chin, Research Scientist, Discovery Partners Institute
Ephemeral Social Networking – Connecting from Offline to Online
Abstract:
Today, people are bombarded with recommendations from people on online social networks such as LinkedIn. Often, people forget to add other people from events to online social networks like LinkedIn. Our project proposes a platform that can be deployed at physical events that records this social proximity from people encountering each other and their social interactions at these events using Bluetooth directly from mobile phones. In this talk, I will first explain the vision of ephemeral social networking and why we need to capture ephemeral social networks at events. Next, I will explain about insights gathered from a survey that study how people connect with others, find people to connect with, and professional networking at events. This will help motivate for the design of a prototype to connect with people from offline to online that has been built so far to support the recording of proximity interactions for ephemeral social networks and the research used to create this design. Finally, I will then explain about how this can be deployed at events and can be used to build a recommendation algorithm to recommend people and groups to connect to from the event onto people’s online social networks.
Bio:
Dr. Alvin Chin is a Research Scientist at Discovery Partners Institute (DPI), University of Illinois System and also is part of DPI’s AI Practice where he helps in conducting Responsible AI research. He holds a PhD in Computer Science from the University of Toronto, and a Masters in Software Engineering and Bachelors in Computer Engineering from the University of Waterloo in Canada. Dr. Chin has over 15 years of experience in industry working for organizations such as Nokia, Microsoft, BMW and RXO, and working on applied R&D projects in recommendation systems, mobile social networking, ubiquitous computing, human-computer interaction, web systems, data science and analytics, big data and IoT, and machine learning and AI. His current research interests are in Responsible AI, Generative AI, and using AI for improving human connection and social networking. Specifically, he is passionate in how we can improve connecting people from events (in-person and online). He published an op-ed in the Chicago Tribune with Prof. Lav Varshney of UIUC on AI safety in 2023. He has published over 20 patents and 30 publications in the above areas. He was an Adjunct Professor at DePaul University for 4 years teaching data science and machine learning courses to undergraduate and graduate students. Dr. Chin is an IEEE Senior Member and ACM Senior Member and actively volunteers in professional organizations where he was previously the Chair for the IEEE Chicago Section (2023-2024) and is currently Chair for ACM Chicago, Chair for IEEE Computer Society Chicago, Chair for IEEE Vehicular Technology Society Chicago, and Co-Chair for the IEEE Chicago Climate Sustainability Local Group as well as Co-Chair for the IEEE Chicago Quantum Computing Local Group. More information about Dr. Chin can be found at his website at https://www.alvinychin.com.
Diego Gomez-Zara, Assistant Professor, University of Notre Dame
Unleashing the Metaverse: A Study of Collaborations in Virtual Reality
Abstract:
The challenging business conditions over the past years have accelerated a shift to remote work by normalizing working from home on a large scale. Current technological advances allow us to envision workplaces supported by metaverse technologies. In this talk, I will describe how metaverse technologies can enhance team collaboration and communication. The results show the differences and unique values of these technologies for collaboration and creativity tasks done by teams.
Bio:
Diego Gómez-Zará (he/him) is an Assistant Professor of Computer Science and Engineering at the University of Notre Dame. His research focuses on how social computational systems help people organize and collaborate. His work has been at the forefront of computational social science, human-computer interaction, and network science. Before joining Notre Dame, he was a postdoctoral fellow at Northwestern University’s Kellogg School of Management and received his Ph.D. in Technology and Social Behavior at Northwestern University. His recent publications include work in recommender systems, team formation, diversity, and virtual reality. This research has won best paper awards at top conferences in human-computer interaction, including CHI, CSCW, and IUI. His research has been supported by the Alfred P. Sloan Foundation, DARPA, National Science Foundation, Microsoft Research, IBM, Amazon Research, and Slack Inc.
Posters:
- Title: Ephemeral Social Networking: Connecting from Offline to Online
Authors: Billy Huang (UIUC and DPI), Justin Chan (UC Boulder), Joshua Garcia (UIC), Nathalie Pastor (UIC), Aria Barve (IMSA), Deen Kareem (IMSA), Philip Yu (UIC), Kevin Leicht (DPI), Alvin Chin (DPI)
Abstract: We attend in-person professional events, but we often forget who we met and where. For example, we may have forgotten to give our business card or add someone we met to an online social network like LinkedIn. Often, we miss opportunities to network with people who were nearby or were unaware that they attended the event. Our research investigates how we can capture those missed opportunities using the concept of opportunistic networking inspired by the “Familiar Stranger” paper by Paulos and Goodman (2002). At an event, you may repeatedly encounter the same person, making them feel “familiar,” yet you do not actually know them, making them a “stranger”. We propose a platform that can be deployed at physical events that records this social proximity from people encountering each other and their social interactions at these events using Bluetooth and activity sensors directly from mobile phones. Our platform will construct an encounter interaction graph and use clustering and deep learning algorithms to detect groups along with social network analysis and social theory to detect enduring interaction structures. Combined with activity recognition, location and event semantics, our research will detect ephemeral social networks, that is, groups that are formed through the encounters recorded by our platform during social activities at the event. That data and analysis will be used to build a recommendation algorithm to recommend people to connect to from the event based on homophily and proximity. - Title: Detection and Categorization of Needs during Crises Based on Twitter Data
Author: Pingjing Yang, University of Illinois Urbana-Champaign
Abstract: The Ukraine-Russia conflict has brought sizable detrimental impact to the global energy, food, finance, and manufacturing industries, as well to many affected people. In this paper, we use Twitter (now X) to automatically identify who needs what from text data and how the types of needs that we categorized and standardize evolved throughout this conflict. Our findings suggest that the Ukraine expresses a need for weapons, Russia for land, Europe for gas, and America for leadership. The majority of needs expressed on Twitter during this conflict are related to the categories transportation, military, health and medical, financial and money, energy, and essential items (food, water, shelter, non-food items). Stated needs changed as the conflict escalated or fell into stalemate. Needs also varied depending on the tweet’s location, with tweets from Ukraine’s neighboring countries being related to food and medicine, while tweets from non-neighboring countries stated needs for clothing and tents. Tweets written in Ukrainian and Russian shared similar need terms, such as medicines and kits, compared to English tweets, which expressed needs such as ammunition and humanitarian aid. Our comparison of needs across four different disaster events, namely this conflict, an earthquake, a major hurricane, and the COVID-19 pandemic, showed how needs differ depending on the nature of the crisis and how domain-adjustment of needs categories is necessary. We contribute to the crisis informatics literature by (1) validating a methodology for using tweets to study the demand and supply of things that different stakeholders need during crisis events and (2) testing, comparing, and improving the fit of widely used need classification schemas for studying crisis from different domains. - Title: Improving Awareness and Understanding of Alzheimer’s Disease and Related Dementias (ADRD) Among Latino Caregivers Through AI-Based Digital Interventions
Authors: Mridvika Suresh (UIC), Paola Reyes (UIC), Ash Kandari (UIC), Crystal Glover (UIC), David Marquez (UIC), Nikita Soni (UIC), Mohan Zalake (UIC)
Abstract: There is a significant knowledge gap about Alzheimer’s Disease and Related dementia (ADRD) among Latino caregivers due to limited access to culturally and linguistically appropriate resources, increasing stress and burden. Familismo emphasizes family support and home caregiving, making ADRD education critical. We leveraged AI technology to create an AI-PROMOTORA that provides educational content and support to Latino caregivers, addressing the gap in a culturally sensitive manner. Using mixed methods research, we combined qualitative and quantitative approaches involving middle-aged Latino ADRD caregivers. Four focus groups were used to assess the content, format, and acceptability of the AI-PROMOTORA intervention. Results found that caregivers struggled with their role and how to provide care, which had a significant emotional impact. The interactive AI persona was user-friendly, and the intervention helped them explore ADRD topics and find information effortlessly. This research offers a scalable solution to educate caregivers effectively by addressing cultural and literacy barriers. - Title: Text, Text + Gesture, or Speech + Text + Gesture? Comparing User Preferences for Interaction Modalities in AI-Based Image Editing Interfaces
Authors: Shanghao Li (UIC), Kenan Alghythee (UIC), Subha Ilamathy (UIC), Trung Bui (UIC), Kevin Smith (UIC), Nikita Soni (UIC)
Abstract: Recent advances in LLMs have enabled AI-driven image editing via text prompts, but prior work shows that users often struggle to convey abstract visual concepts—such as spatial relationships and object proportions—using text alone. While alternative input modalities hold promise for supporting more natural interactions, it remains unclear how they can be effectively integrated into AI-assisted image editing. We conducted a user study with 42 participants to compare how natural and intuitive users find AI-based image editing using three input modalities (text only, text + gesture, and speech + text + gesture), and in what ways these modalities support users’ intent expression. Our ongoing analysis will provide important empirical insights into how—and for which types of images editing tasks—users prefer different modalities to communicate their intent, and how access to these input methods impacts cognitive load. Our findings will inform the design of intuitive and effective multimodal interactions for future AI-based image editing interfaces. - Title: Towards Scalable Detection of Intimate Partner Infiltration on Smartphones
Authors: Weisi Yang (Northwestern University), Shinan Liu (University of Chicago), Feng Xiao (Georgia Institute of Technology), Nick Feamster (University of Chicago), Stephen Xia (Northwestern University)
Abstract: Intimate Partner Infiltration (IPI) is a form of Intimate Partner Violence (IPV) where an abuser gains access to a victim’s mobile device to monitor or control their activity. Unlike traditional cyber threats, IPI abusers exploit physical proximity and trust to circumvent standard defensive mechanisms, making detection particularly difficult. We present AID, an automated tool that continuously monitors user behavior on smartphones to detect unauthorized or suspicious activity. Designed with stealth and privacy in mind, AID operates without visible interfaces and adapts to each user through a brief calibration phase. In a 27-participant study, AID achieved an F1 score of 98.1% with a low false positive rate of 4%. Our findings suggest that AID can serve as a complementary forensic tool for digital safety clinics, offering a scalable way to support at-risk individuals facing IPI in mobile environments.
In preparation for the workshop, please complete this Networking Survey as part of the research for Alvin Chin and his work on Ephemeral Social Networking: https://forms.gle/eYPA6X3upigV6ETXA
If you have any questions about this event, please email alvinc@uillinois.edu.
