Abstract
Student ratings of instruction are an important means of assessment within universities and have been the focus of much study over the last 50 years. Until very recently it has been difficult to perform meaningful analysis of student narrative comments given that most universities collected them as hand-written notes. This work uses statistical and text mining techniques to analyze a data set consisting of over 1 million student comments that were collected using an online process. The methodology makes use of positive and negative “category vectors” representing instructor characteristics and a domain-specific lexicon. Sentiment analysis is used to detect and gauge attitudes embedded in comments about each category. The methodology is validated using three approaches, two quantitative and one qualitative. While useful to individual instructors and administrators, it is only through data mining that student perceptions of teaching can be analyzed en masse to inform and influence the educational process.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Abbreviations
- KWIC:
-
Keyword in context
- MOOC:
-
Massively open online courses
- NAR1:
-
What are some positive characteristics or strengths of the course and/or instructor?
- NAR2:
-
What are some negative characteristics or weaknesses of the course and/or instructor?
- Q10:
-
How would you rate the difficulty level of this course, compared to other courses you have taken so far at Ole Miss?
- Q11:
-
How would you rate the instructor’s overall performance in this course?
- SEEQ:
-
Students’ evaluation of education quality
References
Feldman, K.A.: Effective college teaching from the students’ and faculty’s view: matched and mismatched priorities. Res. High. Educ. 28(4), 291–329 (1988)
Marsh, H.W., Bailey, M.: Multidimensional students’ evaluations of teaching effectiveness. J. Higher Educ. 64(1), 1–18 (1993)
Cashin, W.E.: Student ratings of teaching: the research revisited. IDEA paper No. 32. center for faculty evaluation and development, Kansas State University, Manhattan, 1995
Rindermann, H.: Generalizability of multidimensional student ratings of university instruction across courses and teachers. Res. High. Educ. 42(4), 377–399 (2001)
Abrami, P.C., d’Apollonia, S., Rosenfield, S.: The dimensionality of student ratings of instruction: what we know and what we do not. In: Perry, R.P., Smart, J.C. (eds.) The Scholarship of Teaching and Learning in Higher Education: An Evidence-Based Perspective, pp. 385–456. Springer, The Netherlands (2007)
Jin, W., Ho, H., Srihar, R.: OpinionMiner: a novel machine learning system for web opinion mining and extraction. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1195–1204. ACM, New York (2009)
Kim, S.M., Calvo, R.A.: Sentiment analysis in student experiences of learning. In: Baker, R.S.J.D., Merceron, A., Pavlik Jr., P.I. (eds.) Proceedings of 3rd International Conference on Educational Data Mining, pp. 111–120. International Educational Data Mining Society, Pittsburgh (2010)
Cashin, W.E.: Student ratings of teaching: recommendations for use. IDEA paper No. 22. Technical report, Center for Faculty Evaluation and Development, Kansas State University, Manhattan, 1990
Stowell, J., Addison, W., Smith, J.: Comparison of online and classroom-based student evaluations of instruction. Assess. Eval. High. Educ. 37(4), 465–473 (2012)
Avancini, H., Lavelli, A., Magnini, B., Sebastiani, F., Zonoli, R.: Expanding domain-specific lexicons by term categorization. In: ACM Symposium on Applied Computing, pp. 793–797. ACM, New York (2003)
Sahlgren, M., Coster, R.: Using bag-of-concepts to improve the performance of support vector machines in text categorization. In: Proceedings of 20th International Conference on Computational Linguistics, Geneva, pp. 487–493. Association for Computational Linguistics, Stroudsburg (2004)
Liu, B.: Sentiment analysis and subjectivity. In: Indurkhya, N., Damerau, F.J. (eds.) Handbook of Natural Language Processing, pp. 627–666. CRC Press, Boca Raton (2010). (Chapman and Hall/CRC Machine Learning and Pattern Recognition series)
Liu, B. (ed.): Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data, 2nd edn. Springer, Heidelberg (2011)
Simmons, L., Conlon, S., Mukhopadhyay, S., Yang, J.A.: Computer aided content analysis of online reviews. J. Comput. Inf. Syst. 52(1), 43–55 (2011)
Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-based methods for sentiment analysis. Comput. Linguist. 37(2), 267–307 (2011)
Neviarouskaya, A., Prendinger, H., Ishizuka, M.: SentiFul: a lexicon for sentiment analysis. IEEE Trans. Affect. Comput. 2(1), 22–36 (2011)
Leong, C.K., Lee, Y.H., Mak, W.K.: Mining sentiments in SMS texts for teaching evaluation. Expert Syst. Appl. 39(3), 2584–2589 (2012)
Vialardi, C., Bravo, J., Shafti, L., Ortigosa, A.: Recommendation in higher education using data mining techniques. In: Barnes, T., Desmarais, M., Romero, R., Ventura, S. (eds.) Proceedings of 2nd International Conference on Educational Data Mining, pp. 190–199. International Educational Data Mining Society, Cordoba (2009)
Marsh, H.W.: SEEQ: a reliable, valid, and useful instrument for collecting students’ evaluations of university teaching. Br. J. Educ. Psychol. 52, 77–95 (1982)
Hu., M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 168–177. ACM, New York (2004)
Luhn, H.P.: Keyword-in-context index for technical literature. Am. Doc. 11(4), 288–295 (1960)
SentiWordNet, http://sentiwordnet.isti.cnr.it/
Big Huge Thesaurus, http://words.bighugelabs.com/
Dey, L., Haque, M.: Opinion mining from noisy text data. Int. J. Doc. Anal. Recogn. 12(3), 205–226 (2009)
Jia, L., Yu, C., Meng, W.: The effect of negation on sentiment analysis and retrieval effectiveness. In: Proceedings of 18th ACM International Conference on Information and Knowledge Management, pp. 1827–1830. ACM, New York (2009)
Qiu, G., Liu, B., Bu, J., Chen, C.: Opinion word expansion and target extraction through double propagation. Comput. Linguist. 37(1), 9–27 (2011)
LingPipe, http://alias-i.com/lingpipe/
Hardy, N.: Online ratings: fact or fiction. New Dir. Teach. Learn. 2003(96), 31–38 (2003)
Elsie, M.: Hood outstanding teaching award at the University of Mississippi, http://www.olemiss.edu/news/hood_award/
Melville, P., Gryc, W., Lawrence, R.: Sentiment analysis of blogs by combining lexical knowledge with text classification. In: Proceedings of 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1275–1284. (2009)
Paltoglou, G., Thelwall, M.: A study of information retrieval weighting schemes for sentiment analysis. In: Proceedings of 48th Annual Meeting of the Association for Computational Linguistics, pp. 1386–1395. Association for Computational Linguistics, Stroudsburg (2010)
Agarwal, B., Mittal, N.: Optimal feature selection for sentiment analysis. In: Gelbukh, A. (ed.) Computational Linguistics and Intelligent Text Processing, vol. 7817, pp. 13–24. LNCSSpringer, Heidelberg (2013)
Elberrichi, Z., Rahmoun, A., Bentaalah, M.: Using WordNet for text categorization. Int. Arab. J. Inf. Technol. 5(1), 16–24 (2008)
Campagni, R., Merlini, D., Sprugnoli, R., Verri, M. C.: Comparing examination results and course evaluation: a data mining approach. In: Didamatica 2013, pp. 883–892. Scuola Superiore Sant′Anna, Pisa (2013)
Sap Hana, http://www.saphana.com/
Acknowledgments
This research was made possible through the support of several University of Mississippi units: The Office of the Provost; The Center for Excellence in Teaching and Learning; and The Office of Information Technology. The authors wish to thank Sarah Hill for her help in coordinating the qualitative assessment process.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Gates, K., Wilkins, D., Conlon, S., Mossing, S., Eftink, M. (2014). Maximizing the Value of Student Ratings Through Data Mining. In: Peña-Ayala, A. (eds) Educational Data Mining. Studies in Computational Intelligence, vol 524. Springer, Cham. https://doi.org/10.1007/978-3-319-02738-8_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-02738-8_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02737-1
Online ISBN: 978-3-319-02738-8
eBook Packages: EngineeringEngineering (R0)