Opinion mining and emotion recognition applied to learning environments

被引：62

作者：

Barron Estrada, Maria Lucia ^{[1
]}

Zatarain Cabada, Ramon ^{[1
]}

Oramas Bustillos, Raul ^{[2
]}

Graff, Mario ^{[3
]}

机构：

[1] Tecnol Nacl Mexico, Inst Tecnol Culiacan, Juan de Dios Batiz 310 Pte, Culiacan 80220, Sinaloa, Mexico

[2] Univ Autonoma Occidente, Blvd Lola Beltran, Culiacan 80220, Sinaloa, Mexico

[3] INFOTEC Aguascalientes Circuito, Tecnopolo Sur 112, Aguascalientes 20313, Aguascalientes, Mexico

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2020年 / 150卷

关键词：

Opinion mining; Sentiment analysis; Deep learning; Evolutionary algorithms; Machine learning; Intelligent learning environments; SENTIMENT ANALYSIS;

D O I：

10.1016/j.eswa.2020.113265

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a comparison among several sentiment analysis classifiers using three different techniques - machine learning, deep learning, and an evolutionary approach called EvoMSA - for the classification of educational opinions in an Intelligent Learning Environment called ILE-Java. To make this comparison, we develop two corpora of expressions into the programming languages domain, which reflect the emotional state of students regarding teachers, exams, homework, and academic projects, among others. A corpus called sentiTEXT has polarity (positive and negative) labels, while a corpus called eduSERE has positive and negative learning-centered emotions (engaged, excited, bored, and frustrated) labels. From the experiments carried out with the three techniques, we conclude that the evolutionary algorithm (EvoMSA) generated the best results with an accuracy of 93% for the corpus sentiTEXT, and 84% for the corpus eduSERE. (C) 2020 Elsevier Ltd. All rights reserved.

引用

页数：12

共 55 条

[21]

El-Halees A, 2011, COMM COM INF SC, V180, P107

[22]

Felbo Bjarke, 2017, USING MILLIONS EMOJI, P1615

[23]

Graff M., 2018, CORR

[24] Semantic Genetic Programming for Sentiment Analysis [J].

Graff, Mario ;

Tellez, Eric S. ;

Jair Escalante, Hugo ;

Miranda-Jimenez, Sabino .

NEO 2015, 2017, 663 :43-65

[25]

Hinojosa J.A., 2016, AFFECTIVE NORMS 875, P272, DOI [10.3758/s13428-015-0572-5, DOI 10.3758/S13428-015-0572-5]

[26] Term-weighting learning via genetic programming for text classification [J].

Jair Escalante, Hugo ;

Garcia-Limon, Mauricio A. ;

Morales-Reyes, Alicia ;

Graff, Mario ;

Montes-y-Gomez, Manuel ;

Morales, Eduardo F. ;

Martinez-Carranza, Jose .

KNOWLEDGE-BASED SYSTEMS, 2015, 83 :176-189

[27] A Convolutional Neural Network for Modelling Sentences [J].

Kalchbrenner, Nal ;

Grefenstette, Edward ;

Blunsom, Phil .

PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2014, :655-665

[28]

Kechaou Z., 2011, 2011 IEEE Global Engineering Education Conference (EDUCON), P1032, DOI 10.1109/EDUCON.2011.5773275

[29] ALGA: Adaptive lexicon learning using genetic algorithm for sentiment analysis of microblogs [J].

Keshavarz, Hamidreza ;

Abadeh, Mohammad Saniee .

KNOWLEDGE-BASED SYSTEMS, 2017, 122 :1-16

[30]

Kim Yoon, 2014, Encyclopediaof Microfluidics and Nanofluidics, P1746, DOI DOI 10.3115/V1/D14-1181

← 1 2 3 4 5 6 →