Abstract:
In this research, the case of intent classification for Customer Relation Management (CRM) how to handle complaints as a domain to be followed up, where datasets are extracted from the conversation on Twitter. The research objectives support three key findings to comparing the CNNs and BRNNs model to intent recognition by vectorization text: (1) Which architecture performs better (accuracy) depends on how important it is to semantically understand the whole sequence and (2) Learning rate changes performance relatively smoothly, while the optimal result iterated by change hidden size and batch size result in large fluctuations. (3) Last, how word vectorization is able to define sub-domain of the complaints by word vector classification.
