Tag: Publication

Posted on

Serendyze

Serendyze

Led by: Mahmood Jasim, Christopher Collins, Ali Sarvghad, Narges Mahyar

Related Papers:
PDF Supporting Serendipitous Discovery and Balanced Analysis of Unstructured Text with Interaction-Driven Metrics and Bias-Mitigating Suggestions
CHI Talk

In this study, we investigate how supporting serendipitous discovery and analysis of short free-form texts, such as product review can encourage readers to explore texts more comprehensively prior to decision-making. We propose two interventions — Exploration Metrics that help readers understand and track their exploration patterns through visual indicators and a Bias Mitigation Model that maximizes knowledge discovery by suggesting readers sentiment and semantically diverse reviews. We designed, developed, and evaluated a text analytics system called Serendyze, where we integrated these interventions. We asked 100 crowd workers to use Serendyze to make purchase decisions based on product reviews. Our evaluation suggests that exploration metrics enable readers to efficiently cover more reviews in a balanced way, and suggestions from the bias mitigation model influence readers to make confident data-driven decisions. We discuss the role of user agency and trust in text-level analysis systems and their applicability in domains beyond review exploration

If you are interested in working on or learning more about this project, please contact Mahmood Jasim at mjasim@cs.umass.edu

Posted on

RisingEMOTIONS accepted to C&C 2021 – Congratulations Mahmood & Prof. Mahyar!

RisingEMOTIONS accepted to ACM Creativity & Cognition 2021

Carolina Aragón, Mahmood Jasim and Narges Mahyar recently had their paper “RisingEMOTIONS: Bridging Art and Technology to Increase Public Engagement with Climate Change” accepted to ACM Creativity & Cognition 2021. It will appear at the conference in June. Congratulations to all on a job well done!

Paper Abstract: In response to the threat posed by sea-level rise, coastal cities must rapidly adapt and transform vulnerable areas to protect endangered communities. As such, raising awareness and engaging affected communities in planning for adaptation strategies is critical. However,in the US, public engagement with climate change is low, especially among underrepresented populations. To address this challenge,we designed and implemented RisingEMOTIONS, a site-specific collaborative art installation situated in East Boston that combines public art with digital technology. The installation depicts the impacts of sea-level rise by visualizing local projected flood levels and the public’s emotions toward this threat. The community’s engagement with our project demonstrated the potential for public art to create interest and raise awareness of climate change. We discuss the potential for continued growth in the way that digital tools and public art can support equitable resilience planning through increased public engagement.

Posted on

CommunityPulse to appear in DIS 2021 – Congratulations Mahmood, Prof. Sarvghad & Prof. Mahyar!

CommunityPulse to appear in DIS 2021 – Congratulations Mahmood Jasim, Prof. Sarvghad & Prof. Mahyar!

Recently, Mahmood Jasim, Enamul Hoque, Ali Sarvghad and Narges Mahyar had their paper “CommunityPulse: Facilitating Community Input Analysis by Surfacing Hidden Insights, Reflections, and Priorities” accepted to ACM Designing Interactive Systems (DIS) 2021. Congratulations to all involved!

Paper Abstract: Increased access to online engagement platforms has created a shift in civic practice, enabling civic leaders to broaden their outreach tocollect a larger number of community input, such as comments and ideas. However, sensemaking of such input remains a challenge dueto the unstructured nature of text comments and ambiguity of human language. Hence, community input is often left unanalyzed andunutilized in policymaking. To address this problem, we interviewed 14 civic leaders to understand their practices and requirements.We identified challenges around organizing the unstructured community input and surfacing community’s reflections beyond binarysentiments. Based on these insights, we built CommunityPulse, an interactive system that combines text analysis and visualization toscaffold different facets of community input. Our evaluation with another 15 experts suggests CommunityPulse’s efficacy in surfacingmultiple facets such as reflections, priorities, and hidden insights while reducing the required time, effort, and expertise for communityinput analysis.

Posted on

Our lab had 5 papers accepted this summer, including to CSCW and BELIV.

Our lab had 5 full papers accepted this summer, including to CSCW and BELIV.

Below are the 5 papers which were accepted. Congratulations to all of the authors for their successful submissions!

  • Rehabilitation Games in Real-World Clinical Settings: Practices, Challenges, and Opportunities by Hee-Tae Jung, Taiwoo Park, Narges Mahyar, Sungji Park, Taekyeong Rye, Yangsoo Kim, Sunghoon Ivan Lee (ACM TOCHI, will be presented at ACM CHI 2021)
  • Designing Technology for Sociotechnical Problems: Challenges & Considerations by Narges Mahyar, Mahmood Jasim, and Ali Sarvghad (CG&A)
  • Looking to the Past to Visualize the Present: Revisiting W.E.B. Du Bois’ Abolitionist Visualizations by Andrew Cunningham, Alyxander Burns, and Narges Mahyar (IEEE VIS Poster)
  • CommunityClick:  Capturing  and  Reporting  Community  Feedback  from  Town Halls to Improve Inclusivity by Mahmood  Jasim,  Pooya  Khaloo,  Somin  Wadhwa, Amy  X.  Zhang,  Ali Sarvghad,  and  Narges  Mahyar (CSCW)
  • How to evaluate data visualizations across different levels of understanding by Alyxander Burns, Cindy Xiong, Steven Franconeri, Alberto Cairo, Narges Mahyar (BELIV workshop, held in conjunction with IEEE VIS)
Posted on

Two papers to appear in Late-Breaking Work – CHI 2020

We are proud to announce that two of our lab’s papers were selected for publication in CHI 2020 Late-Breaking Works! See below for information about each paper.

Towards Understanding Desiderata for Large-Scale Civic Input Analysis
Mahmood Jasim, Ali Sarvghad, Enamul Hoque Prince, Narges Mahyar

Advancement in digital civics and the emergence of online platforms have enabled vast amounts of community members to share their input on various civic proposals. Civic leaders, who gather, analyze, and make critical decisions based on community input, struggle to make sense of large-scale unstructured community input due to lack of time, analytical skills, and specialized technologies. In this qualitative study, we investigated civic leaders’ requirements that can accelerate the community input analysis process and help them to gain actionable insights to make better decisions. This study is our first step towards exploring the design of community input analysis technologies for civic leaders to facilitate civic decision-making.


Exploring How International Graduate Students in the US Seek Support
Tamanna Motahar, Mahmood Jashim, Syed Ishtiaque Ahmed, Narges Mahyar

International Graduate Students are an integral part of the United States (US) higher education ecosystem. However, they face enormous challenges while transitioning to the US due to cultural shock, language barriers, and intense academic pressure. These issues can cause poor mental health. Social technology have the potential to help individuals during socio-cultural transitions through social support. The relative ease of access and ubiquity of these technologies make them a candidate for supporting these students as well. However, little is known about the support-seeking process of International Graduate Students. In this paper, we tried to explore this complex process of support seeking and identified different dynamics.