Aspect-Based Sentiment Analysis of Social Media Data With Pre-Trained Language Models

There is a great scope in utilizing the increasing content expressed by users on social media platforms such as Twitter. This study explores the application of Aspect-based Sentiment Analysis (ABSA) of tweets to retrieve fine-grained sentiment insights. The Plantbased food domain is chosen as an area of focus. To the best of our knowledge this is the first time ABSA task is done for this sector and it is distinct from standard food products because different and controversial aspects arise and opinions are polarized. The choice is relevant because these products can help in meeting the sustainable development goals and improve the welfare of millions of animals. Pre-trained BERT,"Bidirectional Encoder Representations with transformers", is fine-tuned for this task and stands out because it was trained to learn from all the words in the sentence simultaneously using transformers. The aim was to develop methods to be applied on real life cases, therefore lowering the dependency on labeled data and improving performance were the key objectives. This research contributes to existing approaches of ABSA by proposing data processing techniques to adapt social media data for ABSA. The scope of this project presents a new method for the aspect category detection task (ACD) which does not rely on labeled data by using regular expressions (Regex). For aspect the sentiment classification task (ASC) a semi-supervised learning technique is explored. Additionally Part-of-Speech (POS) tags are incorporated into the predictions. The findings show that Regex is a solution to eliminate the dependency on labeled data for ACD. For ASC fine-tuning BERT on a small subset of data was the most accurate method to lower the dependency on aspect level sentiment data.