Experiences with the Introduction of AI-based Tools for Moderation Automation of Voice-based Participatory Media Forums
This work provides a case study on AI automation for routine tasks, which is incremental and relevant for researchers and practitioners using voice-based technologies in developing regions.
The authors tackled the problem of automating moderation in voice-based participatory media forums by introducing AI tools for filtering blank/noisy audios, transcribing speech, and extracting metadata, resulting in time and cost savings as reported in a case study with a social enterprise in India.
Voice-based discussion forums where users can record audio messages which are then published for other users to listen and comment, are often moderated to ensure that the published audios are of good quality, relevant, and adhere to editorial guidelines of the forum. There is room for the introduction of AI-based tools in the moderation process, such as to identify and filter out blank or noisy audios, use speech recognition to transcribe the voice messages in text, and use natural language processing techniques to extract relevant metadata from the audio transcripts. We design such tools and deploy them within a social enterprise working in India that runs several voice-based discussion forums. We present our findings in terms of the time and cost-savings made through the introduction of these tools, and describe the feedback of the moderators towards the acceptability of AI-based automation in their workflow. Our work forms a case-study in the use of AI for automation of several routine tasks, and can be especially relevant for other researchers and practitioners involved with the use of voice-based technologies in developing regions of the world.