# Computational Analysis of Insurance Complaints: GEICO Case Study

arXiv: https://arxiv.org/abs/1806.09736 · HTML: https://mlsanity.com/paper/1806.09736/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2018.

## Built on by (most cited first, 3 of 3)

- [NLP-based detection of systematic anomalies among the narratives of consumer complaints](https://mlsanity.com/paper/2308.11138/) (2023)
- [Automotive Parts Assessment: Applying Real-time Instance-Segmentation Models to Identify Vehicle Parts](https://mlsanity.com/paper/2202.00884/) (2022)
- [Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement](https://mlsanity.com/paper/2504.14068/) (2025)

## Abstract (arXiv)

The online environment has provided a great opportunity for insurance policyholders to share their complaints with respect to different services. These complaints can reveal valuable information for insurance companies who seek to improve their services; however, analyzing a huge number of online complaints is a complicated task for human and must involve computational methods to create an efficient process. This research proposes a computational approach to characterize the major topics of a large number of online complaints. Our approach is based on using the topic modeling approach to disclose the latent semantic of complaints. The proposed approach deployed on thousands of GEICO negative reviews. Analyzing 1,371 GEICO complaints indicates that there are 30 major complains in four categories: (1) customer service, (2) insurance coverage, paperwork, policy, and reports, (3) legal issues, and (4) costs, estimates, and payments. This research approach can be used in other applications to explore a large number of reviews.