Sentiment analysis on educational datasets: a comparative evaluation of commercial tools

Sentiment analysis systems have been gaining increasing popularity for extracting information regarding students' affective state. Developing such systems from scratch is a challenging task, thus, many studies employ commercial, general-purpose tools that are not domain-specific. The aim of the...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς: DOLIANITI, FOTEINI S., IAKOVAKIS, DIMITRIOS, DIAS, SOFIA B., HADJILEONTIADOU, SOFIA J., DINIZ, JOSE A., NATSIOU, GEORGIA, TSITOURIDOU, MELPOMENI, BAMIDIS, PANAGIOTIS D., HADJILEONTIADIS, LEONTIOS J.
Μορφή: Online
Γλώσσα:English
Έκδοση: Urray 2019
Θέματα:
Διαθέσιμο Online:https://pasithee.library.upatras.gr/ejupUNESCOchair/article/view/2987
Περιγραφή
Περίληψη:Sentiment analysis systems have been gaining increasing popularity for extracting information regarding students' affective state. Developing such systems from scratch is a challenging task, thus, many studies employ commercial, general-purpose tools that are not domain-specific. The aim of the present work is to comparatively evaluate the performance of five well-known commercial/academic sentiment analysis tools on two educational datasets and contrast it with the performance of educational domain-specific tools, at document and sentence level. Findings suggest that: a) different tools work better for specific datasets and analysis levels, b) depending on the dataset, a general-purpose tool might be a viable solution, and c) any method, domain-specific or general-purpose one, should be evaluated before employed.