Spyridon Tzimiris

Mr. Spyridon Tzimiris

Department of Informatics, Ionian University, Corfu, Greece
orcid
Ph. D. Candidate - Ionian University, Department of Informat...

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 July 2025 in Electronics
Verified
Journal Article
Open access
PDF file
Spyridon TzimirisSpyridon Tzimiris
Spyridon Tzimiris
Stefanos NikiforosStefanos Nikiforos
Stefanos Nikiforos
Maria Nefeli NikiforosMaria Nefeli Nikiforos
Maria Nefeli Nikiforos
Despoina MouratidisDespoina Mouratidis
Despoina Mouratidis
Katia Lida KermanidisKatia Lida Kermanidis
Katia Lida Kermanidis
This research investigates topic-based sentiment classification in Greek educational-related data using transformer-based language models. A comparative evaluation is conducted on GreekBERT, XLM-r-Greek, mBERT, and Palobert using three original sentiment-annotated datasets representing parents of students with functional diversity, school directors, and teachers, each capturing diverse educational perspectives. The analysis examines both overall sentiment performance and topic-specific evaluations across four thematic classes: (i) Material and Technical Conditions, (ii) Educational Dimension, (iii) Psychological/Emotional Dimension, and (iv) Learning Difficulties and Emergency Remote Teaching. Results indicate that GreekBERT consistently outperforms other models, achieving the highest overall F1 score (0.91), particularly excelling in negative sentiment detection (F1 = 0.95) and showing robust performance for positive sentiment classification. The Psychological/Emotional Dimension emerged as the most reliably classified category, with GreekBERT and mBERT demonstrating notably high accuracy and F1 scores. Conversely, Learning Difficulties and Emergency Remote Teaching presented significant classification challenges, especially for Palobert. This study contributes significantly to the field of sentiment analysis with Greek-language data by introducing original annotated datasets, pioneering the application of topic-based sentiment analysis within the Greek educational context, and offering a comparative evaluation of transformer models. Additionally, it highlights the superior performance of Greek-pretrained models in capturing emotional detail, and provides empirical evidence of the negative emotional responses toward Emergency Remote Teaching.

24 January 2023 in Education and Information Technologies
Verified
Journal Article
Open access
PDF file
Spyridon TzimirisSpyridon Tzimiris
Spyridon Tzimiris
Stefanos NikiforosStefanos Nikiforos
Stefanos Nikiforos
Katia Lida KermanidisKatia Lida Kermanidis
Katia Lida Kermanidis
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.

1 January 2023 in International Journal of Information and Education Technology
Verified
Journal Article
Open access
Spyridon TzimirisSpyridon Tzimiris
Spyridon Tzimiris
Stefanos NikiforosStefanos Nikiforos
Stefanos Nikiforos
KKKatia Lida Kermanidis
Katia Lida Kermanidis
The present research examines the way in which Emergency Remote Teaching (ERT) affected students with Special Educational Needs and/or Disability (SEND) during the COVID-19 pandemic. Qualitative descriptive analysis by hand and AI-based/linguistic analysis was performed on the interviews of 12 parents of students with SEND. The results revealed a). how students responded to those special learning conditions, b). how the special educational needs or disabilities of those children affected their attendance on the online courses, and c). how their parents judged the educational dimension of ERT, along with any changes noticed in the psychological and emotional state of their children. Parents highlighted the overall negative impact of ERT on children with SEND.

29 December 2023 in European Journal of Engineering and Technology Research
Verified
Journal Article
Open access
PDF file
Spyridon TzimirisSpyridon Tzimiris
Spyridon Tzimiris
MNMaria Nefeli Nikiforos
Maria Nefeli Nikiforos
Stefanos NikiforosStefanos Nikiforos
Stefanos Nikiforos
KKKatia Lida Kermanidis
Katia Lida Kermanidis
This research delves into the experiences of primary school directors during the abrupt transition to Emergency Remote Teaching (ERT) due to the Covid-19 pandemic. Through semi-structured interviews, the organization and implementation of online classes, associated challenges, and potential improvements were scrutinized. Findings underscored a lack of preparedness, yet acknowledged ERT as a vital tool during the crisis. Recommendations included the improvement of technological support, designing a well-planned strategy, creating appropriate teaching content, comprehensive staff training, and tailoring the educational content to fit students’ learning styles or special needs. A Linguistic Text Analysis approach, employing word clouds, treemaps, and sentiment analysis charts to graphically depict complex patterns in the data, enriched our understanding of the ERT transition, shedding light on subtler nuances and insights. This study contributes valuable knowledge, offering a roadmap for the future development of robust, flexible, and inclusive educational policies and practices, particularly in crisis situations. The dataset is an invaluable asset for policymakers, providing critical insights and highlighting the challenges and opportunities that arise.

21 March 2025 in Information
Verified
Journal Article
Open access
PDF file
Spyridon TzimirisSpyridon Tzimiris
Spyridon Tzimiris
Stefanos NikiforosStefanos Nikiforos
Stefanos Nikiforos
Maria Nefeli NikiforosMaria Nefeli Nikiforos
Maria Nefeli Nikiforos
Despoina MouratidisDespoina Mouratidis
Despoina Mouratidis
Katia Lida KermanidisKatia Lida Kermanidis
Katia Lida Kermanidis
This study explores the application of transformer-based language models for automated Topic Classification in qualitative datasets from interviews conducted in Modern Greek. The interviews captured the views of parents, teachers, and school directors regarding Emergency Remote Teaching. Identifying key themes in this kind of interview is crucial for informed decision-making in educational policies. Each dataset was segmented into sentences and labeled with one out of four topics. The dataset was imbalanced, presenting additional complexity for the classification task. The GreekBERT model was fine-tuned for Topic Classification, with preprocessing including accent stripping, lowercasing, and tokenization. The findings revealed GreekBERT’s effectiveness in achieving balanced performance across all themes, outperforming conventional machine learning models. The highest evaluation metric achieved was a macro-F1-score of 0.76, averaged across all classes, highlighting the effectiveness of the proposed approach. This study contributes the following: (i) datasets capturing diverse educational community perspectives in Modern Greek, (ii) a comparative evaluation of conventional ML models versus transformer-based models, (iii) an investigation of how domain-specific language enhances the performance and accuracy of Topic Classification models, showcasing their effectiveness in specialized datasets and the benefits of fine-tuned GreekBERT for such tasks, and (iv) capturing the complexities of ERT through an empirical investigation of the relationships between extracted topics and relevant variables. These contributions offer reliable, scalable solutions for policymakers, enabling data-driven educational policies to address challenges in remote learning and enhance decision-making based on comprehensive qualitative evidence.