Sentiment Analysis to Evaluate Teaching Performance

Sentiment Analysis to Evaluate Teaching Performance

Paola Adinolfi (University of Salerno, Fisciano, Italy), Ernesto D'Avanzo (University of Salerno, Fisciano, Italy), Miltiadis D. Lytras (The American College of Greece, Greece), Isabel Novo-Corti (University of A Coruna, A Coruna, Spain) and Jose Picatoste (University Autonoma of Madrid, A Coruna, Spain)
Copyright: © 2016 |Pages: 22
DOI: 10.4018/IJKSR.2016100108


The aim of this work is to review a specific learning analytics method - sentiment analysis - in the field of Higher Education, showing how it is employed to monitor student satisfaction on different platforms, and to propose an architecture of Sentiment Analysis for Higher Education purposes, which trace and unify what emerges from the literature review. First, a literature review is carried out, which proves the widespread and increasing interest of the communities, of both scholars and practitioners, in the use of sentiment analysis in the field of Higher Education. The analysis, focused on three different e-learning domains, identifies weaknesses and gaps, and in particular the lack of a unifying approach which is able to deal with the different domains. Secondly, a prototype architecture – LADEL (Learning Analytics Dashboard for E-Learning) - is introduced, which is able to deal with the different e-learning domains. Some preliminary experiments are carried out, highlighting some limitations and open issues, as stimulus to continue the development of the platform.
Article Preview

1. Motivation And Background

(Hazelkorn, 2013) claims that university rankings mechanisms in use are subject to several drawbacks such as, for example, measurement accuracy, measuring the university as a whole institution, and the way data is being collected for measuring specific indicators at universities. For instance, only the average quality of a university is measured, while individual subjects are not considered in the computation. And different compilers have adopted different methods to produce these rankings (Berbegal-Mirabent & Ribeiro-Soriano, 2015). Moreover, indicators such as university reputation have a higher influence value than some others (Olcay & Bulu, 2016), especially on social media (Bunzel, 2007; Kietzmann, Hermkens, McCarthy & Silvestre, 2011). In this sense it appears unsurprising that Higher Education institutions turned to social media strategies to target and attract new students (Constantinides & Zinck Stagno, 2012). Furthermore, relevant educational factors such as quality of teaching or the quality of student experience are taken into account but only marginally (Hazelkorn, 2013), even if students use social media daily and, as such, they are well acquainted with their use (Westerman, Daniel & Bowman, 2016; Siamagka & Christodoulides, 2016). Not surprisingly, therefore, there haven’t been new attempts of constructing rankings mechanisms that seek to incorporate student satisfaction (Vidal, 2016) and content analysis of news media coverage (Friedrichsmeier & Marcinkowski, 2016). For instance, some findings indicated that instructors, from any discipline or culture, could deliver courses through social media platforms thanks to different features provided by social media tools, that encourage, for their part, students’ participation (Kilis, Gülbahar, & Rapp, 2016). Other inquiries show how numbers of instructors are turning to social networking sites to communicate with students, since instructor credibility seems to increase when students are engaged with his social posting with respect to the only scholar posting activity of the teacher (Johnson, 2011).

Complete Article List

Search this Journal:
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing