Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPT
This work assesses the potential of general AI models like ChatGPT for affective computing, indicating they are useful generalists but not yet replacements for specialized models in this domain.
The study evaluated ChatGPT's performance on three affective computing tasks—big-five personality prediction, sentiment analysis, and suicide tendency detection—finding it comparable to Word2Vec and BoW baselines but inferior to task-specialized RoBERTa, with ChatGPT showing robustness against noisy data.
ChatGPT has shown the potential of emerging general artificial intelligence capabilities, as it has demonstrated competent performance across many natural language processing tasks. In this work, we evaluate the capabilities of ChatGPT to perform text classification on three affective computing problems, namely, big-five personality prediction, sentiment analysis, and suicide tendency detection. We utilise three baselines, a robust language model (RoBERTa-base), a legacy word model with pretrained embeddings (Word2Vec), and a simple bag-of-words baseline (BoW). Results show that the RoBERTa trained for a specific downstream task generally has a superior performance. On the other hand, ChatGPT provides decent results, and is relatively comparable to the Word2Vec and BoW baselines. ChatGPT further shows robustness against noisy data, where Word2Vec models achieve worse results due to noise. Results indicate that ChatGPT is a good generalist model that is capable of achieving good results across various problems without any specialised training, however, it is not as good as a specialised model for a downstream task.