Post-pandemic pedagogy: Emergency remote teaching impact on students with functional diversity.

The Covid-19 outbreak caused transition from face-to-face teaching to Emergency Remote Teaching (ERT). Due to the hastily and disorganized implementation of ERT considerable difficulties were caused for all the students. Aim of the present study was to investigate (i) parents' views of students with functional diversity regarding ERT during the Covid-19 pandemic and (ii) how their children's functional diversity affected participation in ERT. ERT proved to be an even greater challenge for those students, who faced various learning, psychological and technical problems that further hindered the learning process. In the current research, the views of 12 parents of students with functional diversity were collected with semi-structured interviews. A Modern Greek dataset of qualitative humanistic-linguistic data was created. A novel type of data analysis, combining qualitative descriptive analysis by hand and Artificial Intelligence (AI)-based linguistic analysis was performed on the interview text. Results revealed (i) how those students responded to ERT, (ii) the way that their functional diversity affected their attendance on the online courses and (iii) how their parents evaluate the educational dimension of ERT along with any changes noticed in their children's psychological and emotional state. Parents' evaluations disclosed the overall negative impact of ERT on their children and presented their suggestions for meeting their children's special needs in case of ERT appliance in the future. The current research is considered significant as it investigates ERT impact on K-12 students with functional diversity during the Covid-19 pandemic, based on authentic humanistic data. Our research contributes on (i) the creation of this kind of dataset, as this particular group of students is hard to come by and their collection constitutes a significant contribution and (ii) the two-fold way data analysis methodology, which is novel, combining linguistic and qualitative processes (semantic and sentiment analysis), providing important findings.

Bullying in Virtual Learning Communities.

Bullying through the internet has been investigated and analyzed mainly in the field of social media. In this paper, it is attempted to analyze bullying in the Virtual Learning Communities using Natural Language Processing (NLP) techniques, mainly in the context of sociocultural learning theories. Therefore four case studies took place. We aim to apply NLP techniques to speech analysis on communication data of online communities. Emphasis is given on qualitative data, taking into account the subjectivity of the collaborative activity. Finally, this is the first time such type of analysis is attempted on Greek data.

Opinion Mining for Educational Video Lectures.

The search for relevant educational videos is a time consuming process for the users. Furthermore, the increasing demand for educational videos intensifies the problem and calls for the users to utilize whichever information is offered by the hosting web pages, and choose the most appropriate one. This research focuses on the classification of user views, based on the comments on educational videos, into positive or negative ones. The aim is to give users a picture of the positive and negative comments that have been recorded, so as to provide a qualitative view of the final selection at their disposal. The present paper's innovation is the automatic identification of the most important words of the verbal content of the video lectures and the filtering of the comments based on them, thus limiting the comments to the ones that have a substantial semantic connection with the video content.