In one aspect, a computerized method for operating computerized neural networks for modelling CSR-customer relationships includes the step of receiving a user query. The user query comprises a set of digital text from a customer as input into an online CSR system. The method includes the step of filtering out unnecessary content of the user query. The method includes the step of splitting filtered user query in a sentence wise manner. The method includes the step of feeding the tokenized user query into a contextualized word representation model. The method includes the step of generating a set of context-aware feature vectors from the contextualized word representation model. With the set of context-aware feature vectors, the method implements a decision-making function to generate an identified customer query. The method includes the step of receiving an agent response, wherein the agent response is a response to the user query, and wherein the agent response comprises a set of digital text from an agent. With an LSTM network, the method generates a user query tensor vector. With the LSTM network, generating an agent query tensor vector. The method includes the step of concatenating the user query tensor vector and the agent query tensor vector to produce a single tensor, wherein the single tensor is processable by a neural network.