Exploring the Ideal Depth of Neural Network when Predicting Question Deletion on Community Question Answering

TL;DR

This paper investigates how neural network depth affects the accuracy of predicting question deletions in Community Question Answering platforms, revealing optimal depths and limitations related to vanishing gradients and computational costs.

Contribution

It provides empirical analysis on the relationship between neural network depth and prediction accuracy for question deletion, highlighting optimal configurations and challenges.

Findings

Deep networks outperform shallow ones up to a point

Accuracy plateaus and declines with excessive depth due to vanishing gradients

Achieves over 90% accuracy with 2-10 hidden layers

Abstract

In recent years, Community Question Answering (CQA) has emerged as a popular platform for knowledge curation and archival. An interesting aspect of question answering is that it combines aspects from natural language processing, information retrieval, and machine learning. In this paper, we have explored how the depth of the neural network influences the accuracy of prediction of deleted questions in question-answering forums. We have used different shallow and deep models for prediction and analyzed the relationships between number of hidden layers, accuracy, and computational time. The results suggest that while deep networks perform better than shallow networks in modeling complex non-linear functions, increasing the depth may not always produce desired results. We observe that the performance of the deep neural network suffers significantly due to vanishing gradients when large number of hidden layers are present. Constantly increasing the depth of the model increases accuracy initially, after which the accuracy plateaus, and finally drops. Adding each layer is also expensive in terms of the time required to train the model. This research is situated in the domain of neural information retrieval and contributes towards building a theory on how deep neural networks can be efficiently and accurately used for predicting question deletion. We predict deleted questions with more than 90\% accuracy using two to ten hidden layers, with less accurate results for shallower and deeper architectures.