A Feasibility Experiment on the Application of Predictive Coding to Instant Messaging Corpora

TL;DR

This paper explores the feasibility of applying predictive coding with machine learning to classify informal instant messaging data, demonstrating a cost-effective approach with improved performance on a real dataset.

Contribution

It introduces a workflow combining message grouping, feature selection, and logistic regression to adapt predictive coding for instant messages, enhancing baseline models with dimensionality reduction.

Findings

Effective grouping of messages into daily chats improves classification.

Dimensionality reduction enhances model performance.

Cost savings demonstrated through the methodology.

Abstract

Predictive coding, the term used in the legal industry for document classification using machine learning, presents additional challenges when the dataset comprises instant messages, due to their informal nature and smaller sizes. In this paper, we exploit a data management workflow to group messages into day chats, followed by feature selection and a logistic regression classifier to provide an economically feasible predictive coding solution. We also improve the solution's baseline model performance by dimensionality reduction, with focus on quantitative features. We test our methodology on an Instant Bloomberg dataset, rich in quantitative information. In parallel, we provide an example of the cost savings of our approach.