In plain words: Reviews are turned into a graph where related words and entities are linked nodes, and a network passes information along those links to catch connections that plain text models miss, on top of pre-trained language models. It judged review sentiment more accurately than models that read text alone.
Abstract
With the growth of textual data across online platforms, sentiment analysis has become crucial for extracting insights from user-generated content. While traditional approaches and deep learning models have shown promise, they cannot often capture complex relationships between entities. In this paper, we propose leveraging Relational Graph Convolutional Networks (RGCNs) for sentiment analysis, which offer interpretability and flexibility by capturing dependencies between data points represented as nodes in a graph. We demonstrate the effectiveness of our approach by using pre-trained language models such as BERT and RoBERTa with RGCN architecture on product reviews from Amazon and Digikala datasets and evaluating the results. Our experiments highlight the effectiveness of RGCNs in capturing relational information for sentiment analysis tasks.
Asal Khosravi, Zahed Rahmati, Ali Vefghi
arXiv:2404.13079 · cs.CL, cs.LG · submitted Apr 16, 2024
abstract · pdf · html
Some of my favorite use cases to do here are in entity resolution / data cleaning during document ingest, mining social media interactions, and analyzing financial data (loan risk, ...). They all used to largely follow the flow here, just add feature engineering and classification decisions specific to the problem at hand. Especially for scale & automation scenarios where quality matters, this stuff helps.
How I think about this space has changed significantly with modern transformers compared to the BERT-era ones here. The paper feels closer to what we (and others) were doing before GPT4 came out. Now that LLMs can 'reason', not just embed, a lot more has opened up during the feature extraction, learning, and deciding phases. Basically pick up any new KG paper using LLMs, there is a lot to keep up with.
Happy to chat if folks are doing fun things here. We are always looking for good projects in this space as there is nuance and esp with LLMs changing so much. Exciting times!