Distributional sentiment modeling and anomaly detection for consumer complaint assessment
Not on the map. Why?
Abstract (arXiv)
Sentiment analysis is a common tool for converting unstructured text into quantitative signals in finance and risk management. Yet most applications reduce the output to a discrete polarity label or a single predictive feature, overlooking the distributional structure of sentiment intensity in consumer complaint narratives. In this paper we treat negative sentiment in consumer complaints as a bounded continuous variable and study its full distribution rather than a single label. We score each narrative with a transformer classifier, model the scores with Beta distributions, and compare the fitted distributions of meritorious and non-meritorious complaints through the Kullback Leibler divergence and the squared Hellinger distance. The fitted distributions are then linked with dollar amounts and company response outcomes to construct anomaly diagnostics that flag complaints whose textual severity is inconsistent with the recorded relief. We find that the two groups have strongly overlapping distributions, so negative sentiment intensity is not a sharp classifier of outcomes on its own; combined with monetary and categorical attributes, it isolates unusually severe complaints for operational risk monitoring. Treating sentiment analysis as continuous distributional measurement, this study links sentiment extraction, bounded response modeling, and anomaly detection in a unified framework for consumer complaint assessment.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 46 references that are in the map. First posted on arXiv 14 Sep 2026.
Builds on
23 of 46 references.
References · 23
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
- 2024A Survey of Large Language Models in Finance (FinLLMs)cited by 79
- 2024Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Reviewcited by 53
- 2024Large Language Models for Anomaly and Out-of-Distribution Detection: A Surveycited by 27
- 2024Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysiscited by 11
- 2024Comparison of Topic Modelling Approaches in the Banking Contextcited by 10
- 2024RiskLabs: Predicting Financial Risk Using Large Language Model based on Multimodal and Multi-Sources Datacited by 6
- 2024Iterative Data Generation with Large Language Models for Aspect-based Sentiment Analysiscited by 6
- 2024Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Modelscited by 5
11 more
- 2023NLP-based detection of systematic anomalies among the narratives of consumer complaintscited by 3
- 2024Log-concave Density Estimation with Independent Componentscited by 3
- 2025Scalable and robust regression models for continuous proportional datacited by 3
- 2024Policy Gradient-Driven Noise Maskcited by 2
- 2024Shrinkage Estimators for Beta Regression Modelscited by 2
- 2024Extended-support beta regression for [0, 1] responsescited by 2
- 2024HELLINGER-UCB: A novel algorithm for stochastic multi-armed bandit problem and cold start problem in recommender systemcited by 1
- 2024A Model-Free Kullback-Leibler Divergence Filter for Anomaly Detection in Noisy Data Seriescited by 1
- 2024Generative Sentiment Analysis via Latent Category Distribution and Constrained Decodingcited by 1
- 2025Bayesian Optimization over Bounded Domains with the Beta Product Kernelcited by 1
- 2026From Complaint Narratives to Monetary Relief: A Hybrid Machine Learning Framework for CFPB Consumer Complaintscited by 1
Built on by
Not cited yet.