SentimentPulse: Temporal-Aware Custom Language Models vs. GPT-3.5 for Consumer Sentiment

(Conference Workshop Poster Publication)

Access paper here

Abstract: Large Language Models are trained on an extremely large corpus of text data to allow better generalization, but this blessing can also become a curse and significantly limit their performance in a subset of tasks. In this work, we argue that LLMs are notably behind well-tailored and specifically designed models where the temporal aspect is important in making decisions, and the answer depends on the timespan of available training data. We prove our point by comparing two major architectures: first, SentimentPulse, a real-time consumer sentiment analysis approach that leverages custom language models and continual learning techniques, and second, GPT-3.5, which is tested on the same data. Unlike foundation models lacking temporal context, our custom language model is pre-trained on time-stamped data, uniquely suited for real-time applications.