# Modeling the Severity of Complaints in Social Media

arXiv: https://arxiv.org/abs/2103.12428 · HTML: https://mlsanity.com/paper/2103.12428/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 43 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors](https://mlsanity.com/paper/1811.09362/) (2018)
- [Automatically Identifying Complaints in Social Media](https://mlsanity.com/paper/1906.03890/) (2019)
- [Analyzing Political Parody in Social Media](https://mlsanity.com/paper/2004.13878/) (2020)
- [Joint Modelling of Emotion and Abusive Language Detection](https://mlsanity.com/paper/2005.14028/) (2020)
- [Predicting Twitter User Socioeconomic Attributes with Network and Language Information](https://mlsanity.com/paper/1804.04095/) (2018)
- [Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum](https://mlsanity.com/paper/1808.08538/) (2018)
- [Complaint Identification in Social Media with Transformer Networks](https://mlsanity.com/paper/2010.10910/) (2020)
- [Integrating Multimodal Information in Large Pretrained Transformers](https://mlsanity.com/paper/1908.05787/) (2019)
- [Cross-lingual Emotion Intensity Prediction](https://mlsanity.com/paper/2004.04103/) (2020)
- [Identifying leading indicators of product recalls from online reviews using positive unlabeled learning and domain adaptation](https://mlsanity.com/paper/1703.00518/) (2017)

## Built on by (most cited first, 7 of 7)

- [Explainable Identification of Dementia from Transcripts using Transformer Networks](https://mlsanity.com/paper/2109.06980/) (2021)
- [Automatic Identification and Classification of Bragging in Social Media](https://mlsanity.com/paper/2203.05840/) (2022)
- [Point-of-Interest Type Prediction using Text and Images](https://mlsanity.com/paper/2109.00602/) (2021)
- [Dimensions of Online Conflict: Towards Modeling Agonism](https://mlsanity.com/paper/2311.03584/) (2023)
- [Deciphering the complaint aspects: Towards an aspect-based complaint identification model with video complaint dataset in finance](https://mlsanity.com/paper/2503.00054/) (2025)
- [Analyzing the Intensity of Complaints on Social Media](https://mlsanity.com/paper/2204.09366/) (2022)
- [When Words Can't Capture It All: Towards Video-Based User Complaint Text Generation with Multimodal Video Complaint Dataset](https://mlsanity.com/paper/2509.19952/) (2025)

## Abstract (arXiv)

The speech act of complaining is used by humans to communicate a negative mismatch between reality and expectations as a reaction to an unfavorable situation. Linguistic theory of pragmatics categorizes complaints into various severity levels based on the face-threat that the complainer is willing to undertake. This is particularly useful for understanding the intent of complainers and how humans develop suitable apology strategies. In this paper, we study the severity level of complaints for the first time in computational linguistics. To facilitate this, we enrich a publicly available data set of complaints with four severity categories and train different transformer-based networks combined with linguistic information achieving 55.7 macro F1. We also jointly model binary complaint classification and complaint severity in a multi-task setting achieving new state-of-the-art results on binary complaint detection reaching up to 88.2 macro F1. Finally, we present a qualitative analysis of the behavior of our models in predicting complaint severity levels.