Opinion mining and emotion recognition applied to learning environments

被引：59

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

[41]

Rosenthal Sara, 2019, ARXIV191200741

[42] Understanding the Role of Negative Emotions in Adult Learning and Achievement: A Social Functional Perspective [J].

Rowe, Anna D. ;

Fitness, Julie .

BEHAVIORAL SCIENCES, 2018, 8 (02)

[43]

Rowe AD, 2017, ENABLING POWER ASSES, V5, P159, DOI 10.1007/978-981-10-3045-1_11

[44]

Smith T.C., 1995, PROC IJCAI 95 WORKSH, P17

[45]

Spector L., 1999, ADV GENETIC PROGRAM, V3

[46] An automated text categorization framework based on hyperparameter optimization [J].

Tellez, Eric S. ;

Moctezuma, Daniela ;

Miranda-Jimenez, Sabino ;

Graff, Mario .

KNOWLEDGE-BASED SYSTEMS, 2018, 149 :110-123

[47] A simple approach to multilingual polarity classification in Twitter [J].

Tellez, Eric S. ;

Miranda-Jimenez, Sabino ;

Graff, Mario ;

Moctezuma, Daniela ;

Suarez, Ranyart R. ;

Siordia, Oscar S. .

PATTERN RECOGNITION LETTERS, 2017, 94 :68-74

[48]

Tul Q., 2017, INT J ADV COMP SCI A, V8, DOI [10.14569/IJACSA.2017.080657, DOI 10.14569/IJACSA.2017.080657]

[49]

Wang J, 2016, PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2016), VOL 2, P225

[50]

Wang X, 2015, PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, P1343

← 1 2 3 4 5 6 →