Text-Based Detection of On-Hold Scripts in Contact Center Calls

TL;DR

This paper introduces a natural language processing model that detects on-hold scripts in contact center calls to improve agent monitoring and customer satisfaction.

Contribution

It formulates on-hold script detection as a multiclass text classification task and fine-tunes RuBERT for high accuracy in identifying relevant dialogue turns.

Findings

High model performance achieved with RuBERT fine-tuning

Effective detection of on-hold and return scripts in call transcripts

Potential to enhance agent monitoring and script adherence

Abstract

Average hold time is a concern for call centers because it affects customer satisfaction. Contact centers should instruct their agents to use special on-hold scripts to maintain positive interactions with clients. This study presents a natural language processing model that detects on-hold phrases in customer service calls transcribed by automatic speech recognition technology. The task of finding hold scripts in dialogue was formulated as a multiclass text classification problem with three mutually exclusive classes: scripts for putting a client on hold, scripts for returning to a client, and phrases irrelevant to on-hold scripts. We collected an in-house dataset of calls and labeled each dialogue turn in each call. We fine-tuned RuBERT on the dataset by exploring various hyperparameter sets and achieved high model performance. The developed model can help agent monitoring by providing a way to check whether an agent follows predefined on-hold scripts.