Mining: Students Comments about Teacher Performance Assessment using Machine Learning Algorithms

The exponential expansion of sentiment analysis is mainly due to the interest of companies to obtainment users’ views about products and services. Likewise, sentiment analysis has been widely and successfully used in publicity and selling strategies as well as behaviour patterns and user preferences identification. In the same way, has been applied to educational areas to increase the learning, and e-learning quality through the mining analysis data on teaching performance assessment or student’s comments. This work describes the development and evaluating the process of a Model called “SocialMining“, which is focused on higher education with the purpose of improve teaching techniques of teachers and recommend courses for teacher improvement, through teacher performance evaluation made by students comments. The SocialMining model analyze students’ comments by means representative machine learning algorithms such as: Support Vector Machines and Random Forest. We applied metrics as evaluation measure to measuring the performance of algorithms. Finally, we have implemented this model in Universidad Politecnica de Aguascalientes (Mexico) and the results obtained show that it is feasible to perform sentiment analysis to classify comments of Teacher Performance Assessment using Machine Learning with high accuracy (85%).

[1]  Jie Zhang,et al.  The multilayer sentiment analysis model based on Random forest , 2016 .

[2]  Hongyan Liu,et al.  Combining user preferences and user opinions for accurate recommendation , 2013, Electron. Commer. Res. Appl..

[3]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  Kent A. Spackman,et al.  Signal Detection Theory: Valuable Tools for Evaluating Inductive Learning , 1989, ML.

[6]  Ron Kohavi,et al.  Guest Editors' Introduction: On Applied Research in Machine Learning , 1998, Machine Learning.

[7]  E. Kirubakaran,et al.  M-Learning Sentiment Analysis with Data Mining , 2012 .

[8]  Rosa M. Carro,et al.  Sentiment analysis in Facebook and its application to e-learning , 2014, Comput. Hum. Behav..

[9]  Chakrit Pong-Inwong,et al.  Teaching Senti-Lexicon for Automated Sentiment Polarity Definition in Teaching Evaluation , 2014, 2014 10th International Conference on Semantics, Knowledge and Grids.

[10]  Uzay Kaymak,et al.  Cohen's kappa coefficient as a performance measure for feature selection , 2010, International Conference on Fuzzy Systems.

[11]  Erwan Scornet,et al.  A random forest guided tour , 2015, TEST.

[12]  D. Stufflebeam,et al.  Teacher Evaluation: Guide to Effective Practice , 1995 .

[13]  Yung-Ming Li,et al.  Deriving market intelligence from microblogs , 2013, Decis. Support Syst..

[14]  Francesco Colace,et al.  SAFE: A Sentiment Analysis Framework for E-Learning , 2014, iJET.

[15]  Chih-Jen Lin,et al.  A Simple Decomposition Method for Support Vector Machines , 2002, Machine Learning.

[16]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[17]  Juana Canul-Reich,et al.  Proposal of a Sentiment Analysis Model in Tweets for improvement of the teaching - learning process in the classroom using a corpus of subjectivity , 2016, Int. J. Comb. Optim. Probl. Informatics.

[18]  Bing Liu,et al.  Sentiment Analysis and Opinion Mining , 2012, Synthesis Lectures on Human Language Technologies.

[19]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[20]  Mihaela Cocea,et al.  Learning Sentiment from Students' Feedback for Real-Time Interventions in Classrooms , 2014, ICAIS.

[21]  Estrella Martínez-Rodrigo,et al.  El microblogging en el proceso de enseñanza-aprendizaje. Una experiencia académica con Twitter , 2014 .

[22]  Jochen L. Leidner,et al.  Handbook of Natural Language Processing (second edition) , 2011 .

[23]  S. Selva Brunda.  IDENTIFYING E-LEARNER'S OPINION USING AUTOMATED SENTIMENT ANALYSIS IN E-LEARNING , 2014 .

[24]  Adam Hjerpe.  Computing Random Forests Variable Importance Measures (VIM) on Mixed Numerical and Categorical Data , 2016 .