Received: 24 January 2018 | Accepted: 29 June 2018 DOI: 10.1002/cae.22059 RESEARCH ARTICLE Opinion mining and emotion recognition in an intelligent learning environment Raúl Oramas Bustillos 1 | Ramón Zatarain Cabada 1 | María Lucía Barrón Estrada 1 | Yasmin Hernández Pérez 2 1 Instituto Tecnológico de Culiacán, Division of Research and Postgraduate Studies, Culiacán, Sinaloa, México 2 Instituto Nacional de Electricidad y Energías Limpias, Tecnologías de la Información, Cuernavaca, México Correspondence Ramón Zatarain Cabada, Instituto Tecnológico de Culiacán, Division of Research and Postgraduate Studies, Juan de Dios Bátiz 310 Pte. Col. Guadalupe, Culiacán, Sinaloa, CP 80220, México. Email: rzatarain@itculiacan.edu.mx Funding information Tecnológico Nacional de México, Grant number: 5731.16-P Abstract In this paper, we present the development of an opinion-mining module. The development of the module consisted of creating an emotion tagged dataset of opinions; implementing an opinion mining module that processes sentences about computer programming, predicting or recognizing their polarity (positive/negative) and their type of emotion (frustrated, bored, excited, engagement, and neutral); and integrating the previous module in an intelligent learning environment. We evaluated the corpus, the accuracy of text polarity, and emotion recognition. The results with respect to polarity are promising (88.26%), however, the results in the detection of emotions are still low (60.0%). The reasons which likely explain these outcomes include a relatively small (7,777 records) and unbalanced corpus. KEYWORDS computer programming learning, intelligent learning environments, opinion mining, sentiment analysis 1 | INTRODUCTION People have opinions and the majority are willing to share them publicly. These pieces of information are valuable assets that can be used for decision making: where to buy something? where to go for dinner? How do people feel doing some activity or visiting some attraction? Many internet sites allow us to express our opinion about several products and services they offer, and users many times rely on these opinions to guide their choices. Users express themselves in social networks like Facebook, Twitter, and Instagram, write public reviews of items they buy in virtual stores like Amazon or eBay, recommend series to watch on streaming services like Netflix or share their comments about movies in Rotten Tomatoes. These kind of web applications have changed the way people interact with each other and their consumption habits by guiding their decisions based on the opinion of other users. Analyzing the diversity of online opinions has a potential impact in commercial, industrial, and academic environments, but the extraction and processing of opinions is a complex and difficult task. Opinion mining (OM) allows the inspection of textual information automatically [29]. OM is one of the most interesting applications of Natural Language Processing (NLP) used in social media applications, whose goal is the evaluation and classification of text with emotionally charged language which expresses or implies positive or negative sentiments [27]. On the other hand, in Virtual Learning Environments, the feedback between teacher (tutor or facilitator) and the student is a valuable instrument in the teaching–learning pro- cess [17,14]. Student feedback can help to understand the student learning behavior. This feedback contains open- ended student opinions and provides meaningful insights for teachers to incorporate changes and improve their course material, strategies, and other teaching elements. Intelligent learning environments (ILE) are used to give personalized and targeted instruction in a particular domain. Java Sensei is an Intelligent Learning Environment [28] 90 | © 2018 Wiley Periodicals, Inc. wileyonlinelibrary.com/cae Comput Appl Eng Educ. 2019;27:90–101