My Publications

This study introduces an Artificial Intelligence (AI)-based proof-of-concept approach to tackle food fraud by using convolutional neural networks (CNNs) and citizen science-generated imagery to predict the country of origin of Cavendish banana cultivars (Musa spp.). A total of 6000 images were collected from iNaturalist, and a CNN classifier was trained to distinguish bananas sourced from six countries. Transfer learning was leveraged, and among nine pre-trained models tested, MobileNetV1 demonstrated the best trade-off between performance and computational efficiency. Following model fine-tuning, data augmentation was implemented to mitigate class imbalance and ensure a dense feature space. The model achieved an average accuracy of 0.86 with Monte Carlo Cross Validation and 0.77 with a 5-Fold Cross Validation. The final selected model attained a validation accuracy of 0.79. Accordingly, this study should be viewed as a foundational proof-of-concept demonstrating the potential of AI for origin detection at the cultivation stage. While the current evaluation framework reflects an early-stage experimental setting, the findings introduce a promising new dimension for proactive food fraud detection. Moving forward, this pipeline provides a foundation that can be expanded and independently validated.

This study presents a systematic literature review evaluating the current state of artificial intelligence (AI) applications in combating food fraud. Following the Kitchenham framework, 69 primary studies from peer-reviewed journals across four academic databases were identified and analyzed. The aim was to examine the types of fraud detected by AI, the food products involved, the specific AI techniques used, and the performance evaluation metrics utilized. Most of the included studies focused on the detection of adulteration and mislabeling, particularly origin and quality mislabeling, with spices, herbs, meat and dairy being the most frequently investigated food product categories. Machine Learning (ML) and Deep Learning (DL) were the primary approaches utilized, ML was the most dominant, with Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs) emerging as the most frequently applied algorithms. Regarding the data types, spectral and imaging data were predominantly used, and most models were developed using supervised approaches. Nevertheless, despite strong model performance with data gathered from controlled environments such as labs, issues such as data availability and interpretability remain. The findings underscore the importance of AI applied in food fraud detection and the need to explore underrepresented fraud types and food categories.

The unprecedented production and sharing of data, opinions, and comments among people on social media and the Internet in general has highlighted sentiment analysis (SA) as a key machine learning approach in scientific and market research. Sentiment analysis can extract sentiments and opinions from user-generated text, providing useful evidence for new product decision-making and effective customer relationship management. However, there are concerns about existing standard sentiment analysis tools regarding the generation of inaccurate sentiment classification results. The objective of this paper is to determine the efficiency of off-the-shelf sentiment analysis APIs in recognizing low-resource languages, such as Greek. Specifically, we examined whether sentiment analysis performed on 300 online ordering customer reviews using the Meaning Cloud web-based tool produced meaningful results with high accuracy. According to the results of this study, we found low agreement between the web-based and the actual raters in the food delivery services related data. However, the low accuracy of the results highlights the need for specialized sentiment analysis tools capable of recognizing only one low-resource language. Finally, the results highlight the necessity of developing specialized lexicons tailored not only to a specific language but also to a particular field, such as a specific type of restaurant or shop.

The unprecedented production and sharing of data, opinions, and comments among people on social media and the Internet in general has highlighted sentiment analysis (SA) as a key machine learning approach in scientific and market research. Sentiment analysis can extract sentiments and opinions from user-generated text, providing useful evidence for new product decision-making and effective customer relationship management. However, there are concerns about existing standard sentiment analysis tools regarding the generation of inaccurate sentiment classification results. The objective of this paper is to determine the efficiency of off-the-shelf sentiment analysis APIs in recognizing low-resource languages, such as Greek. Specifically, we examined whether sentiment analysis performed on 300 online ordering customer reviews using the Meaning Cloud web-based tool produced meaningful results with high accuracy. According to the results of this study, we found low agreement between the web-based and the actual raters in the food delivery services related data. However, the low accuracy of the results highlights the need for specialized sentiment analysis tools capable of recognizing only one low-resource language. Finally, the results highlight the necessity of developing specialized lexicons tailored not only to a specific language but also to a particular field, such as a specific type of restaurant or shop.