Predicting Emotion in Movie Scripts Using Deep Learning

被引：4

作者：

Kim, Dong-Min ^{[1
]}

Lee, Seong-Ho ^{[1
]}

Cheong, Yun-Gyung ^{[1
]}

机构：

[1] Sungkyunkwan Univ, Coll Software, Suwon, South Korea

来源：

2018 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP) | 2018年

基金：

新加坡国家研究基金会;

关键词：

machine learning; deep learning; movie ratings; text mining;

D O I：

10.1109/BigComp.2018.00088

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper we present a machine learning approach that aims to predict an emotion that follows given text segments. For this, we pre-processed a collection of movie scripts to generate a sequence of sentiment values. The sequence is given to a deep learning network to learn the sentiment value to follow. The evaluation result was promising, showing high cosine similarities between the target and the predicted emotion values.

引用

页码：530 / 532

页数：3

共 8 条

[1]

Baccianella S., 2010, P 7 INT C LANG RES O, V10, P2200

[2] The MovieLens Datasets: History and Context [J].

Harper, F. Maxwell ;

Konstan, Joseph A. .

ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS, 2016, 5 (04)

[3]

Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.8.1735, 10.1007/978-3-642-24797-2, 10.1162/neco.1997.9.1.1]

[4]

Huang A., 2008, P 6 NZ COMP SCI RES, V4, P9

[5] Caffe: Convolutional Architecture for Fast Feature Embedding [J].

Jia, Yangqing ;

Shelhamer, Evan ;

Donahue, Jeff ;

Karayev, Sergey ;

Long, Jonathan ;

Girshick, Ross ;

Guadarrama, Sergio ;

Darrell, Trevor .

PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14), 2014, :675-678

[6]

Lee Seong-Ho, 2017, P IEEE INT WORKSH BI

[7]

Loper E., 2002, Nltk: The natural language toolkit

[8] WORDNET - A LEXICAL DATABASE FOR ENGLISH [J].

MILLER, GA .

COMMUNICATIONS OF THE ACM, 1995, 38 (11) :39-41

← 1 →