# Uncertainty-Aware Reward-based Deep Reinforcement Learning for Intent Analysis of Social Media Information

arXiv: https://arxiv.org/abs/2302.10195 · HTML: https://mlsanity.com/paper/2302.10195/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 19 Feb 2023.

## Builds on (most cited first, 5 of 5)

- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [Learning to Compose Words into Sentences with Reinforcement Learning](https://mlsanity.com/paper/1611.09100/) (2016)
- [Learning with Weak Supervision for Email Intent Detection](https://mlsanity.com/paper/2005.13084/) (2020)
- [Aspect Sentiment Triplet Extraction Using Reinforcement Learning](https://mlsanity.com/paper/2108.06107/) (2021)
- [An ontological analysis of misinformation in online social networks](https://mlsanity.com/paper/2102.11362/) (2021)

## Built on by (most cited first, 1 of 1)

- [Opinion-Guided Reinforcement Learning](https://mlsanity.com/paper/2405.17287/) (2024)

## Abstract (arXiv)

Due to various and serious adverse impacts of spreading fake news, it is often known that only people with malicious intent would propagate fake news. However, it is not necessarily true based on social science studies. Distinguishing the types of fake news spreaders based on their intent is critical because it will effectively guide how to intervene to mitigate the spread of fake news with different approaches. To this end, we propose an intent classification framework that can best identify the correct intent of fake news. We will leverage deep reinforcement learning (DRL) that can optimize the structural representation of each tweet by removing noisy words from the input sequence when appending an actor to the long short-term memory (LSTM) intent classifier. Policy gradient DRL model (e.g., REINFORCE) can lead the actor to a higher delayed reward. We also devise a new uncertainty-aware immediate reward using a subjective opinion that can explicitly deal with multidimensional uncertainty for effective decision-making. Via 600K training episodes from a fake news tweets dataset with an annotated intent class, we evaluate the performance of uncertainty-aware reward in DRL. Evaluation results demonstrate that our proposed framework efficiently reduces the number of selected words to maintain a high 95% multi-class accuracy.