Social Media as an Instant Source of Feedback on Water Quality

TL;DR

This study develops a novel framework using neural networks and optimization techniques to automatically analyze social media posts for water quality feedback, achieving high accuracy and outperforming existing methods.

Contribution

The paper introduces a new multi-model fusion framework employing BERT, XLM-RoBERTa, and LSTM with optimization-based weighting for water quality detection from social media.

Findings

Highest individual model F1-score of 0.81 with BERT.

Fusion approach with brute force optimization achieves F1-score of 0.852.

Significant improvement over existing methods.

Abstract

This paper focuses on an important environmental challenge; namely, water quality by analyzing the potential of social media as an immediate source of feedback. The main goal of the work is to automatically analyze and retrieve social media posts relevant to water quality with particular attention to posts describing different aspects of water quality, such as watercolor, smell, taste, and related illnesses. To this aim, we propose a novel framework incorporating different preprocessing, data augmentation, and classification techniques. In total, three different Neural Networks (NNs) architectures, namely (i) Bidirectional Encoder Representations from Transformers (BERT), (ii) Robustly Optimized BERT Pre-training Approach (XLM-RoBERTa), and (iii) custom Long short-term memory (LSTM) model, are employed in a merit-based fusion scheme. For merit-based weight assignment to the models, several optimization and search techniques are compared including a Particle Swarm Optimization (PSO), a Genetic Algorithm (GA), Brute Force (BF), Nelder-Mead, and Powell's optimization methods. We also provide an evaluation of the individual models where the highest F1-score of 0.81 is obtained with the BERT model. In merit-based fusion, overall better results are obtained with BF achieving an F1-score score of 0.852. We also provide comparison against existing methods, where a significant improvement for our proposed solutions is obtained. We believe such rigorous analysis of this relatively new topic will provide a baseline for future research.