PlumX Metrics
Embed PlumX Metrics

Investigating transformer-based models for automated e-governance in Indian Railway using Twitter

Multimedia Tools and Applications, ISSN: 1573-7721, Vol: 83, Issue: 2, Page: 4551-4577
2024
  • 1
    Citations
  • 0
    Usage
  • 12
    Captures
  • 0
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

Article Description

Recently, Twitter has been used as a citizen-engaging platform by Indian Railway Ministry (IRM) for collecting civic issues. However, due to the manual inspection model, a large percentage of complaints are left unaddressed affecting the credibility of the citizen-sourcing mediums. The existing solutions are for English reports and unable to capture the diverse range of code-mixed languages used in the complaints. In this paper, we developed a multilingual cased version of BERT (mBERT) for automated identification of monolingual and code-mixed Hindi-English complaints. In addition to the grievances classification, we also employ BERT multi-label classifier for labelling the tweets with the issues reported in the complaints. The proposed solution approach obtains a weighted f1-score of 82% and overall accuracy of 96% for binary and multilabel tasks, respectively. We compare our results against conventional machine learning algorithms proposed in existing literature. Further, the benchmarking is performed against BERTweet and IndicBERT and observe that the proposed framework outperforms these models. Additionally, a critical analysis is presented on the classified reports and a location-based analysis to visualise the velocity and veracity of complaints across India.

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know