COAL: Convolutional Online Adaptation Learning for Opinion Mining
Iti Chaturvedi, Edoardo Ragusa, Paolo Gastaldo, Erik Cambria · 2020
Thanks to recent advances in machine learning, some say AI is the new engine and data is the new coal. Mining this ‘coal’ from the ever-growing Social Web, however, can be a formidable task. In this work, we address this problem in the context of sentiment analysis using convolutional online adaptation learning (COAL). In particular, we consider semi-supervised learning of convolutional features, which we use to train an online model. Such a model, which can be trained in one domain but also used to predict sentiment in other domains, outperforms the baseline in the range of 5-20%.