Sentiment Analysis: Towards a Tool for Analysing Real-Time Students Feedback

Altrabsheh, Nabeela; Cocea, Mihaela; Fallahkhair, Sanaz

doi:10.1109/ictai.2014.70

Cited by 66 publications

(52 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This finding is consistent with a number of recent studies discussing students' Sentiment analysis (e.g. [9], [8] and [14]).…”

Section: Experiments Results and Discussionsupporting

confidence: 93%

“…Given the importance of obtaining real-time feedback from students to improve educational outcomes, we found that many previous studies have tried to analyse student feedback and extract student sentiment using different techniques and tools. In [8], machine learning techniques, preprocessing levels and the use of neutral class were used to analyse real-time student feedback. It was found that preprocessing the data improved accuracy by 20%.…”

Section: Natural Language Processingmentioning

confidence: 99%

See 1 more Smart Citation

Big data and learning analytics in higher education: Demystifying variety, acquisition, storage, NLP and analytics

Alblawi

Alhamed

2017

2017 IEEE Conference on Big Data and Analytics (ICBDA)

View full text Add to dashboard Cite

Different sectors have sought to take advantage of opportunities to invest in big data analytics and Natural language processing, in order to improve their productivity and competitiveness. Current challenges facing the higher education sector include a rapidly changing and evolving environment, which necessitates the development of new ways of thinking. Interest has therefore increased in analytics as part of the solution to many issues in higher education, including rate of student attrition and learner support. This study provides a comprehensive discussion on big data, learning analytics and use of NLP in higher education. In addition, it introduces an integrated learning analytics solution leveraging a distributed technology system capable of supporting academic authorities and advisors at educational institutions in making decisions concerning individual students.

show abstract

“…This finding is consistent with a number of recent studies discussing students' Sentiment analysis (e.g. [9], [8] and [14]).…”

Section: Experiments Results and Discussionsupporting

confidence: 93%

Section: Natural Language Processingmentioning

confidence: 99%

Big data and learning analytics in higher education: Demystifying variety, acquisition, storage, NLP and analytics

Alblawi

Alhamed

2017

2017 IEEE Conference on Big Data and Analytics (ICBDA)

View full text Add to dashboard Cite

show abstract

“…Most approaches in the sentiment analysis area focus on polarity or opinion classification into positive or negative classes [8], [9], [10]; some researchers also include a neutral class [11], [12]. Other classification tasks focus on subjectivity vs. objectivity [13], on predicting categories of emotions (e.g.…”

Section: Related Studiesmentioning

confidence: 99%

“…The research in this area has been applied to a variety of data sources, such as movie reviews [10], product reviews [17], [18], Facebook data [11] and micro-blog data [12], [19]. In this research reported in this paper we use movie reviews data.…”

Section: Related Studiesmentioning

confidence: 99%

Fuzzy approach for sentiment analysis

Jefferson

Liu

Cocea

2017

2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

Self Cite

View full text Add to dashboard Cite

Sentiment analysis aims to identify the polarity of a document through natural language processing, text analysis and computational linguistics. Over the last decade, there has been much focus on sentiment analysis as the data available on-line has grown exponentially to include many sentiment based documents (reviews, feedback, articles). Many approaches consider machine learning techniques or statistical analysis, but there has been little use of the fuzzy classifiers in this field especially considering the ambiguity of language and the suitability of fuzzy approaches to deal with this ambiguity. This paper proposes a fuzzy rule based system for sentiment analysis, which can offer more refined outputs through the use of fuzzy membership degrees. We compare the performance of our proposed approach with commonly used sentiment classifiers (e.g. Decision Trees, Naïve Bayes) which are known to perform well in this task. The experimental results indicate that our fuzzybased approach performs marginally better than the other algorithms. In addition, the fuzzy approach allows the definition of different degrees of sentiment without the need to use a larger number of classes.

show abstract

“…positive/negative/neutral, and (b) the presence in the feedback of particular emotions related to learning, e.g. excitement and boredom [2], [3]. We also created six visualisations to present the results to the lecturers.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the SA-E System for Analysis of Students’ Real-Time Feedback

Altrabsheh

Cocea

Fallahkhair

et al. 2017

2017 IEEE 17th International Conference on Advanced Learning Technologies (ICALT)

Self Cite

View full text Add to dashboard Cite

Abstract-Students' real-time feedback is acknowledged as an important source of information for teachers/lecturers to improve their teaching and address issues students may have, such as going deeper in some of the materials covered or providing more examples to understand an abstract concept. Previous applications collecting real-time feedback from students through clickers and mobiles typically collect limited information with pre-defined questions, while more recent applications using social media collect such a large volume of information that a lecturer cannot manually process it in real time. We developed the SA-E system for analysing students' real-time feedback provided via social media, and, in this paper, we present the evaluation of this system in real settings with lecturers and students. The results show that lecturers are highly satisfied with the proposed system. In contrast, although the participation of students in providing feedback was high, the students' opinions of the system were between neutral and dislike.

show abstract

Sentiment Analysis: Towards a Tool for Analysing Real-Time Students Feedback

Cited by 66 publications

References 8 publications

Big data and learning analytics in higher education: Demystifying variety, acquisition, storage, NLP and analytics

Big data and learning analytics in higher education: Demystifying variety, acquisition, storage, NLP and analytics

Fuzzy approach for sentiment analysis

Evaluation of the SA-E System for Analysis of Students’ Real-Time Feedback

Contact Info

Product

Resources

About