Predicting Audience's Laughter Using Convolutional Neural Network

TL;DR

This paper introduces a CNN-based approach for humor recognition in TED talk transcripts, demonstrating improved accuracy over traditional methods by automatically learning relevant features from lexical cues.

Contribution

It presents a new humor recognition dataset and systematically compares CNNs with conventional linguistic methods, highlighting CNNs' superior performance and feature learning capabilities.

Findings

CNN achieves higher detection accuracy

CNN automatically learns essential features

Dataset includes diverse speakers and is openly accessible

Abstract

For the purpose of automatically evaluating speakers' humor usage, we build a presentation corpus containing humorous utterances based on TED talks. Compared to previous data resources supporting humor recognition research, ours has several advantages, including (a) both positive and negative instances coming from a homogeneous data set, (b) containing a large number of speakers, and (c) being open. Focusing on using lexical cues for humor recognition, we systematically compare a newly emerging text classification method based on Convolutional Neural Networks (CNNs) with a well-established conventional method using linguistic knowledge. The advantages of the CNN method are both getting higher detection accuracies and being able to learn essential features automatically.