The increasing use of social media platforms for seeking religious information raises critical questions about the interplay of technology, algorithms, and faith. Prior HCI literature has explored users’ algorithmic experience in various domains such as news, music, mental health, etc. However, religion, a highly sensitive and significant domain, remains underexplored within the HCI scholarship. Therefore, we investigate how social media algorithms influence users’ religious content engagement through semi-structured interviews and focus groups with 24 Muslim participants from Bangladesh. Our findings reveal that the benefits of algorithms in the Islamic context are often overshadowed by the significant harm of inappropriate recommendations. As a result, participants envisioned algorithms that actively support their spiritual growth and faith practices. Building on these insights, we outline a potential design space for religion-aware algorithms and propose a conceptual framework of users’ hierarchical religious needs for Islamic content to inform future faith-based technology design.

Abstract Data visualizations are typically not accessible to blind and low‐vision (BLV) users. Automatically generating text descriptions offers an enticing mechanism for democratizing access to the information held in complex scientific charts, yet appropriate procedures for generating those texts remain elusive. Pursuing this issue, we study a single complex chart form: UpSet plots. UpSet Plots are a common way to analyze set data, an area largely unexplored by prior accessibility literature. By analyzing the patterns present in real‐world examples, we develop a system for automatically captioning any UpSet plot. We evaluated the utility of our captions via semi‐structured interviews with (N=11) BLV users and found that BLV users find them informative. In extensions, we find that sighted users can use our texts similarly to UpSet plots and that they are better than naive LLM usage.

Epidemics and pandemics have been affecting human lives since time, and have sometimes altered the course of history. At this very moment, Coronavirus (COVID-19) pandemic has been the defining global health crisis. Now, perhaps for the first time in history, humanity as a whole has undergone major disruptions to life and some form of lockdown. New policies need to be forged by policy-makers for various sectors such as trading, banking, education, etc., to lessen losses and to heal quickly. For efficient policy-making, in turn, some prerequisites needed are historical trend analysis on the pandemic spread, future forecasting, the correlation between the spread of the disease and various socio-economic and environmental factors, etc. Besides, all of these need to be presented in an integrated manner in real-time to facilitate efficient policy-making. Therefore, in this work, we developed a web-based integrated real-time operational dashboard as a one-stop decision support system for COVID-19. In our study, we conducted a detailed data-driven analysis based on available data from multiple authenticated sources to predict the upcoming consequences of the pandemic through rigorous modeling and statistical analyses. We also explored the correlations between disease spread and diverse socio-economic as well as environmental factors. Furthermore, we presented how the outcomes of our work can facilitate both contemporary and future policy-making.

The recent Covid-19 pandemic elucidates the need for a better disease outbreak analysis and surveillance system, which can harness state-of-the-art data mining and machine learning techniques to produce better forecasting. In this regard, understanding the correlation between disease outbreaks and socioeconomic factors should pave the way for such systems by providing useful indicators, which are yet to be explored in the literature to the best of our knowledge. Therefore, in this study, we accumulated data on 72 infectious diseases and their outbreaks all over the globe over a period of 23 years as well as corresponding different socioeconomic data. We, then, performed point-biserial and spearman correlation analysis over the collected data. Our analysis of the obtained correlations demonstrates that various disease outbreak attributes are positively and negatively correlated with different socioeconomic indicators. For example, indicators such as lifetime risk of maternal death, adolescent fertility rate, etc., are positively correlated, while indicators such as life expectancy at birth, measles immunization, etc., are negatively correlated, with disease outbreaks that affect the digestive organ system. In this paper, we find and summarize the correlations between 126 outbreak attributes derived from the characteristics of the 72 diseases in consideration and 192 socioeconomic factors which is a novel contribution to the field of disease outbreak analysis and prediction.