Sentiment Analysis from Students’ Feedback : A Romanian High School Case Study

Marcu, Daniela; Danubianu, Mirela

doi:10.1109/das49615.2020.9108927

Cited by 9 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, we also found papers related to real-time adjustable feedback ( Lee et al, 2019 ), analyses and classification of students’ sentiments towards the educational process ( Marcu and Danubianu, 2020 ), and direct mapping between learning traces typically gathered for learning analytics and a theoretically grounded model of cognition ( Seitlinger et al, 2020 ).…”

Section: Resultsmentioning

confidence: 99%

Applications of Learning Analytics in High Schools: A Systematic Literature Review

Sousa

Alexandre

Mello

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

Learning analytics aims to analyze data from students and learning environments to support learning at different levels. Although learning analytics is a recent field, it reached a high level of maturity, especially in its applications for higher education. However, little of the research in learning analytics targets other educational levels, such as high school. This paper reports the results of a systematic literature review (SLR) focused on the adoption of learning analytics in high schools. More specifically, the SLR followed four steps: the search, selection of relevant studies, critical assessment, and the extraction of the relevant field, which included the main goals, approaches, techniques, and challenges of adopting learning analytics in high school. The results show that, in this context, learning analytics applications are focused on small-scale initiatives rather than institutional adoption. Based on the findings of this study, in combination with the literature, this paper proposes future directions of research and development in order to scale up learning analytics applications in high schools.

show abstract

Section: Resultsmentioning

confidence: 99%

Applications of Learning Analytics in High Schools: A Systematic Literature Review

Sousa

Alexandre

Mello

et al. 2021

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Various computer software, such as “KNIME” (Jović et al , 2014), “Orange Data Mining” (Marcu and Danubianu, 2020), “RapidMiner” (Jović et al , 2014), “R” (Caraka et al , 2020; Hudaefi et al , 2021; Islam and Kaur, 2018; Oza and Naik, 2016), “NVivo” (Alcoforado and Dos Reis, 2020; Hai-Jew, 2017; Hudaefi and Badeges, 2021; Hudaefi and Beik, 2021), “Weka” (Jović et al , 2014) and “Python” have been used in previous works to perform text analytics. In this study, text mining via “R” is used to perform sentiment analysis.…”

Section: Methodsmentioning

confidence: 99%

Mining netizen’s opinion on cryptocurrency: sentiment analysis of Twitter data

Hassan

Hudaefi

Caraka

2021

SEF

View full text Add to dashboard Cite

Purpose This paper aims to explore netizen’s opinions on cryptocurrency under the lens of emotion theory and lexicon sentiments analysis via machine learning. Design/methodology/approach An automated Web-scrapping via RStudio is performed to collect the data of 15,000 tweets on cryptocurrency. Sentiment lexicon analysis is done via machine learning to evaluate the emotion score of the sample. The types of emotion tested are anger, anticipation, disgust, fear, joy, sadness, surprise, trust and the two primary sentiments, i.e. negative and positive. Findings The supervised machine learning discovers a total score of 53,077 sentiments from the sampled 15,000 tweets. This score is from the artificial intelligence evaluation of eight emotions, i.e. anger (2%), anticipation (18%), disgust (1%), fear (3%), joy (15%), sadness (3%), surprise (7%), trust (15%) and the two sentiments, i.e. negative (4%) and positive (33%). The result indicates that the sample primarily contains positive sentiments. This finding is theoretically significant to measure the emotion theory on the sampled tweets that can best explain the social implications of the cryptocurrency phenomenon. Research limitations/implications This work is limited to evaluate the sampled tweets’ sentiment scores to explain the social implication of cryptocurrency. Practical implications The finding is necessary to explain the recent phenomenon of cryptocurrency. The positive sentiment may describe the increase in investment in the decentralised finance market. Meanwhile, the anticipation emotion may illustrate the public’s reaction to the bubble prices of cryptocurrencies. Social implications Previous studies find that the social signals, e.g. word-of-mouth, netizens’ opinions, among others, affect the cryptocurrencies’ movement prices. This paper helps explain the social implications of such dynamic of pricing via sentiment analysis. Originality/value This study contributes to theoretically explain the implications of the cryptocurrency phenomenon under the emotion theory. Specifically, this study shows how supervised machine learning can measure the emotion theory from data tweets to explain the implications of cryptocurrencies.

show abstract

“…Emotion recognition helps stakeholders to describe and analyse the emotions of course participants, usually towards the institute, instructor, and course. For example, Marcu and Danubianu [15] aims to analyse the students' emotions towards the school. To categorise the emotion, they use two models, Plutchik and Ekman, as anger, anticipation (Plutchik only), disgust, fear, joy, sadness, surprise and trust (Plutchik only).…”

Section: A According To Aim and Categorisationmentioning

confidence: 99%

“…6) Machine or manual translation to English: Three of the studies translated the data into English using Google Translate, (Sadriu et al [19], Lwin et al [20] and Lalata et al [23]) sometimes later revised by human whereas another two studies (Marcu and Danubianu [15] and Nikolovski et al [22]) manually translated the data into English. In total, 20.8% of the studies translated the comments that are written in a language rather than English.…”

Section: According To Data Language Size and Labelsmentioning

confidence: 99%