

<?xml version="1.0" encoding="UTF-8"?>
<record>
  <title>Analysis of ChatGPT as a Question-Answering Tool</title>
  <journal>Journal of Digital Information Management</journal>
  <author>Pit Pichappan, M. Krishnamurthy, P. Vijayakumar</author>
  <volume>21</volume>
  <issue>2</issue>
  <year>2023</year>
  <doi>https://doi.org/10.6025/jdim/2023/21/2/50-61</doi>
  <url>https://www.dline.info/fpaper/jdim/v21i2/jdimv21i2_3.pdf</url>
  <abstract>ChatGPT, in recent months, has made a significant impact and exposure in the information world. Many studies have been conducted within a shorter timeframe about its efficiency, reliability, ethics, accuracy and acceptance. Besides, hundreds of opinions and perception-based analyses have also emerged. In this work, we look at the ChatGPT as a question-answering tool. We have used randomly generated prompts to solicit answers and analysed the results from a text analysis angle. The answers are compared with text analysers both manually and statistically. ChatGPT still needs more precision for linguistic effects and fails to meet comprehensive users requirements.</abstract>
</record>
