AIAdnanul Islam

Adnanul Islam

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Adnanul Islam has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Dialogis : A Framework for Designing Human-Centred Video Conferencing Environments

    by Rheinanda Kaniaswari, Alice Chuang, Yusun Jeon, Tom Bartindale, Md Adnanul Islam, Ling Wu, Argens Ng, Delvin Varghese, Arif Perdana, Patrick Olivier

    1. Video conferencing began as a tool for distributed team meetings, built around a narrow set of design assumptions: small groups, shared work tasks, and turn-taking organized around meeting agend...

  • Open Access

    Paroli: Designing for Productive Participation and Engagement in Voice-based Platforms for Rural Workforces

    by Md Adnanul Islam, Muhamad Risqi U. Saputra, Dan Richardson, Tom Bartindale, Patrick Olivier, Delvin Varghese

    Over the last two decades, voice-based platforms (VBPs), including interactive voice response (IVR) and WhatsApp, have shown remarkable promise in bridging the digital divide faced by organizations and communities in international development contexts. However, much work in VBPs has focused simply on community participation, with little focus on how this participation over VBPs can be configured to maximize participant engagement and productivity, especially in rural workforce settings. Across two deployments, with nonprofits supporting rural fisherfolk and tea garden workers, we piloted a VBP unlocking new participation formats in VBPs tailored to specific needs and lived experiences of target workforces to enhance the participation experience. Leveraging telephony, the VBP fosters inclusive and flexible community engagement, facilitating synchronous small group discussions and streamlining both asynchronous and synchronous interactions unique to existing VBPs. Our study further contributes to HCI and CSCW literature by identifying the factors important for sustaining remote workforce engagement in VBPs: (1) community ownership for increasing participation, (2) need for upskilling VBP hosts to increase productivity, and (3) embedding local cues as part of the VBP deployment to maximize uptake.

  • Open Access

    Corrigendum: Bridging the Technical Gap: A Unified Representation Framework for Voice-based Community Engagement Platforms

    by Delvin Varghese, Md Adnanul Islam, Dan Richardson, Muhamad Risqi U. Saputra, Manika Saha, Tom Bartindale, Md. Saddam Hossain Mukta, Rheinanda Kaniaswari, Md. Yousuf, Patrick Olivier

    This is a corrigendum for the article "Bridging the Technical Gap: A Unified Representation Framework for Voice-based Community Engagement Platforms" published in Proc. ACM Hum.-Comput. Interact. 9, 7, Article CSCW277 (November 2025), 39 pages.

  • Open Access

    Bridging the Technical Gap: A Unified Representation Framework for Voice-based Community Engagement Platforms

    by Md Adnanul Islam, Delvin Varghese, Dan Richardson, Muhamad Risqi U. Saputra, Manika Saha, Tom Bartindale, Md. Saddam Hossain Mukta, Rheinanda Kaniaswari, Md. Yousuf, Patrick Olivier

    HCI practitioners in development contexts utilize collaborative digital technologies for community engagement in international development, often mediated through platforms like social media, tele-conferencing, and Interactive Voice Response (IVR). However, the lack of standardized representation approaches for these platforms impedes effective communication among stakeholders. We propose a unified graphical framework for characterizing and representing collaborative platforms, focusing on audio/voice-based engagements. Our framework segments community engagement sessions into engagement formats, characterizing them with preconditions, configurations, and outputs, and visualizes them using state machine-based representations. A field study demonstrates the framework's effectiveness in supporting stakeholder communication for real-life scenarios. We contribute to CSCW literature by providing a standardized approach that offers a common framework/language for discussing, developing, or reconfiguring collaborative platforms. Our findings show that this framework enables non-governmental organizations and researchers to navigate under-explored design spaces, enhancing the utilization of voice-based platforms for engaging distributed marginalized communities.


  • Open Access

    Recordkeeping in Voice-based Remote Community Engagement

    by Adnanul Islam, Dan Richardson, Manika Saha, Delvin Varghese, Tom Bartindale, Pratyasha Saha, Muhamad Risqi U. Saputra, Patrick Olivier

    Driven by pragmatic, cost-related, and environmental factors, voice-based remote community engagement tools (such as Interactive Voice Response) are emerging as a key modality for engaging marginalized communities. These voice-based digital solutions offer new opportunities for distributed community engagement and empowerment, and the ability to capture, store, and access a wide range of different records (i.e., recordings, interactions and contextual metadata) associated with community engagements. This potential for large scale, distributed community record collection necessitates an understanding of inclusive and effective recordkeeping approaches for appraisal, documentation, preservation, and accessibility of different types of records (such as audio recordings, transcripts, reports, and observatory notes) related to voice-based community engagements. Through qualitative analysis of stakeholder focus group discussions with domestic workers (as marginalized community members) and NGOs working in the sector, we present valuable insights and recommendations for the development of recordkeeping approaches tailored to voice-based remote community engagement records.


  • Open Access

    A Design Vocabulary for Scaffolding Group Interaction Archetypes through Synchronous Telephony

    by Dan Richardson, Adnanul Islam, Bronwyn J. Cumbo, Pranita Shrestha, Delvin Varghese, Tom Bartindale, Patrick Olivier

    Multiple HCI projects have demonstrated the potential of digitally-enhanced, synchronous telephony platforms for use with and by resource-limited communities. However, these platforms were each designed to only facilitate a single archetype of community engagement, limiting their capacity for adaptation when contextual or stakeholder requirements change. This paper builds upon these projects to introduce a design vocabulary, grounded in a formal ontology describing the core components necessary to run adaptable, structured engagements through synchronous group telephony. Through a series of scenarios, we present how this design vocabulary can be used to: help design and communicate different models of synchronous audio engagements, describe existing technologies, and highlight other novel ways in which such platforms could be used. We discuss how while under-explored to this point, synchronous telephony platforms can be designed to orchestrate stakeholder engagements with a degree of flexibility previously impossible in remote, offline contexts.


  • Open Access

    Natural Language–Based Conceptual Modelling Frameworks: State of the Art and Future Opportunities

    by Bayzid Ashik Hossain, Saddam Hossain Mukta, Adnanul Islam, Akib Zaman, Rolf Schwitter

    Identifying requirements for an information system is an important task and conceptual modelling is the first step in this process. Conceptual modelling plays a critical role in the information system design process and usually involves domain experts and knowledge engineers who brainstorm together to identify the required knowledge to build an information system. The conceptual modelling process starts with the collection of necessary information from the domain experts by the knowledge engineers. Afterwards, the knowledge engineers use traditional model driven engineering techniques to design the system based on the collected information. Natural language–based conceptual modelling frameworks or systems are used to help domain experts and knowledge engineers in eliciting requirements and building conceptual models from a natural language text. In this article, we discuss the state of the art of some recent conceptual modelling frameworks that are based on natural language. We take a closer look at how these frameworks are built, in particular at the underlying motivation, architecture, types of natural language used (e.g., restricted vs. unrestricted), types of the conceptual model generated, verification support of the requirements specifications as well as the conceptual models, and underlying knowledge representation formalism. We also discuss some future research opportunities that these frameworks offer.


  • Predicting Users’ Eat-Out Preference from Big5 Personality Traits

    by Saddam Hossain Mukta, Akib Zaman, Adnanul Islam, Bayzid Ashik Hossain

  • Open Access

    Data Driven Classification of Opioid Patients Using Machine Learning–An Investigation

    by Lisan Al Amin, Saddam Hossain Mukta, Sezan Mahmud Saikat, Ismail Hossain, Adnanul Islam, Mohiuddin Ahmed, Sami Azam

    The opioid crisis has led to an increased number of drug overdoses in recent years. Several approaches have been established to predict opioid prescription by health practitioners. However, due to the complex nature of the problem, the accuracy of such methods is not yet satisfactory. Dependable and reliable classification of opioid dependent patients from well-grounded data sources is essential. Majority of the previous studies do not focus on the users’ mental health association for opioid intake classification. These studies do not also employ the latest deep learning based techniques such as attention and knowledge distillation mechanism to find better insights. This paper investigates the opioid classification problem by using machine learning and deep learning based techniques. We used structured and unstructured data from the MIMIC-III database to identify intentional and unintentional intake of opioid drugs. We selected 455 patient instances and used traditional machine learning and deep learning to predict intentional and accidental users. We obtained 95% and 64% test accuracy to predict the intentional and accidental users from the structured and unstructured datasets, respectively. We also achieve a distilled knowledge based test accuracy of 76.44% from the integrated above two models. Our research includes an ablation analysis and new insights related to opioid patients are extracted.