FarmChat: A Conversational Agent to Answer Farmer Queries

Mohit Jain, Pratyush Kumar, Ishita Bhansali, Q. Vera Liao, Khai Truong, Shwetak Patel

FarmChat is a novel speech-based conversational system that meets the information needs of low literate rural Indian farmers. The chatbot's intelligence was based on Kisan Call Center logs and inputs from local agri-experts.

Abstract

Farmers constitute 54.6% of the Indian population, but earn only 13.9% of the national GDP. This gross mismatch can be alleviated by improving farmers’ access to information and expert advice (e.g., knowing which seeds to sow and how to treat pests can significantly impact yield). In this paper, we report our experience of designing a conversational agent, called FarmChat, to meet the information needs of farmers in rural India. We conducted an evaluative study with 34 farmers near Ranchi in India, focusing on assessing the usability of the system, acceptability of the information provided, and understanding the user population’s unique preferences, needs, and challenges in using the technology. We performed a comparative study with two different modalities: audio-only and audio+text. Our results provide a detailed understanding on how literacy level, digital literacy, and other factors impact users’ preferences for the interaction modality. We found that a conversational agent has the potential to effectively meet the information needs of farmers at scale. More broadly, our results could inform future work on designing conversational agents for user populations with limited literacy and technology experience.