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.

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.

Voice-based digital platforms are increasingly recognized as powerful tools for fostering community participation and bridging digital divide. These platforms offer unique opportunities for engaging distributed communities, especially those with limited digital literacy and internet access. Despite their potential, the comprehensive impact of voice-based platforms is constrained by challenges concerning design inclusivity, sustainability, and stakeholder empowerment. This systematic review critically examines existing voice-based platforms, identifying key challenges and opportunities for enhancing their effectiveness. Our review reveals that innovative participation archetypes, when supported by inclusive design and robust policy frameworks, can significantly enhance community engagement. Additionally, sustainable business models and stakeholder empowerment are crucial for the long-term viability of these platforms. This study provides actionable insights and a research framework for ICTD researchers and practitioners, emphasizing the need for inclusive, sustainable, and contextually relevant design and development of voice-based solutions to drive sustainable social change and promote digital equity.

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.

Punctuation prediction is critical as it can enhance the readability of machine-transcribed speeches or texts significantly by adding appropriate punctuation. Furthermore, systems like Automatic Speech Recognizer (ASR) produce texts that are unpunctuated, making the readability difficult for humans and also hampers the performance of various natural language processing (NLP) tasks. Such NLP related tasks have been investigated thoroughly for English; however, very limited work is done for punctuation prediction in the Bangla language. In this study, we train a bidirectional recurrent neural network (BRNN) along with Attention model with a plausibly large Bangla dataset. Afterwards, we apply extensive postprocessing techniques for predicting punctuation more accurately with the employed model. Initially, we perform experimentation with a relatively imbalanced dataset, and our model shows promising results F1=56.9 for Period) in punctuation prediction. Later, we also investigate the model’s performance using a balanced Bangla dataset to achieve higher performance scores ( F1=62.2 for Question). Thus, the goal of this study is to propose an efficient approach that can predict punctuation in Bangla texts effectively. Our study also includes investigation on how our postprocessing techniques affect the prediction performance. Being an early attempt for the punctuation prediction in Bangla text, our work is expected to significantly contribute in the NLP field for the Bangla language, and will pave the way for future work with the Bangla language in this direction.

Emotions are psychological traits which are associated with an individuals' thoughts, feelings, behavioral responses, and experiences of pleasure and displeasure. The ability to recognise a conversational partner's emotional state from their speech (and respond accordingly) is a longstanding requirement of a fully capable intelligent virtual agent. However, despite the fact that current approaches to emotion recognition primarily depend upon supervised machine learning models, there are no comprehensive guidelines for emotion label annotation of the corpora used to train such models. We present comprehensive guidelines for consistent and effective annotation of text corpora with emotion labels. In particular, our proposal directly addresses the requirements of multi-label emotion recognition, and we demonstrate how an implementation of our proposed guidelines led to substantially (30%) higher agreement score among human annotators.

Sentiment Analysis (SA) is a Natural Language Processing (NLP) and an Information Extraction (IE) task that primarily aims to obtain the writer’s feelings expressed in positive or negative by analyzing a large number of documents. SA is also widely studied in the fields of data mining, web mining, text mining, and information retrieval. The fundamental task in sentiment analysis is to classify the polarity of a given content as Positive, Negative, or Neutral . Although extensive research has been conducted in this area of computational linguistics, most of the research work has been carried out in the context of English language. However, Bengali sentiment expression has varying degree of sentiment labels, which can be plausibly distinct from English language. Therefore, sentiment assessment of Bengali language is undeniably important to be developed and executed properly. In sentiment analysis, the prediction potential of an automatic modeling is completely dependent on the quality of dataset annotation. Bengali sentiment annotation is a challenging task due to diversified structures (syntax) of the language and its different degrees of innate sentiments (i.e., weakly and strongly positive/negative sentiments). Thus, in this article, we propose a novel and precise guideline for the researchers, linguistic experts, and referees to annotate Bengali sentences immaculately with a view to building effective datasets for automatic sentiment prediction efficiently.