Extracting Valuable Insights from The Handwritten Feedback
Yugandhar Chawale, Prasanna Patwardhan, Rahul Dewani, Ankit More, Varsha D. Jadhav, Mrityunjoy Pandey, Neha Vaishnavi Sharma · 2024
This paper describes the collection and analysis of feedback data which is crucial for evaluating the success of any event and identifying areas of improvement. However, when feedback forms are distributed in paper format, extracting the text responses into a machine-readable format for analysis can be a tedious and error-prone manual process. Optical Character Recognition (OCR) Technology offers an automated solution for digitizing text from scanned documents, but its accuracy can be impacted by various factors like image quality, font styles, and language complexities. This study investigates the use of Gemini 1.5 Pro, a multimodal AI, to extract text data from PDF scans of collected handwritten feedback forms. After evaluation of Gemini’s performance across a range of PDF qualities and comparing its output to manually transcribed data, the results demonstrate Gemini's high accuracy rates, even on lower quality scans, enabling efficient extraction of feedback responses while minimizing manual effort. This solution offers a scalable and reliable approach for educational institutions, professional organizations and other bodies to digitize survey responses for deeper qualitative and quantitative computational techniques.