Search UNB Scholar

About UNB Scholar

UNB Scholar is an institutional repository initiative of UNB Libraries intended to collect, preserve, showcase, and promote the open access scholarly output of the UNB community. Use UNB Scholar to explore specific collections, or search all content in the repository. Material submitted to the repository will also be freely discoverable online through Google and other major search engines.

UNB Libraries welcomes submissions to UNB Scholar. Find out more about depositing your publications!

Communities in UNB Scholar

Select a community to browse its collections.

Recent Submissions

Token-level identification of multiword expressions using pre-trained multilingual language models
(University of New Brunswick, 2023-09) Swaminathan, Raghuraman; Cook, Paul
Multiword expressions (MWEs) are combinations of words where the meaning of the expression cannot be derived from its component words. MWEs are commonly used in different languages and are difficulty to identify. For different NLP tasks such as sentiment analysis and machine translation, it is important that language models automatically identify and classify these MWEs. While considerable work has been done in identifying and classifying MWEs, little work has been done in a cross-lingual setting. In this thesis, we consider novel cross-lingual settings for MWE identification and idiomaticity prediction in which systems are tested on languages that are unseen during training. We use multilingual models of BERT, specifically mBERT, RoBERTa and mDeBERTa. Our findings indicate that pre-trained multilingual language models are able to learn knowledge about MWEs and idiomaticity that is not language-specific. Moreover, we find that training data from other languages can be leveraged to give improvements over monolingual models.
A comparison of machine learning algorithms for zero-shot cross-lingual phishing detection
(University of New Brunswick, 2023-08) Staples, Dakota; Hakak, Saqib; Cook, Paul
Phishing is a major problem worldwide. Existing studies have focused mainly on detecting emails in one language (mostly English). However, detecting emails in multiple languages is challenging due to a lack of datasets. Without ample data from which to learn, the models cannot detect a benign email from a spam email accurately, resulting in false positives and negatives. This research aims to compare the performance of numerous machine learning models and transformers using zero-shot learning for multilingual phishing detection. In a zero-shot learning set-up, the model is trained on one language and tested on another. English, French, and Russian emails are used as the training and testing languages. My results show that, on average, XLM-Roberta performs the best out of all the tested models in terms of accuracy scoring 99% testing on English, 99% testing on French, and 95% testing on Russian.
How to catch a sea monster: acoustic telemetry and stable isotope analysis of Atlantic wolffish (Anarhichas lupus)
(University of New Brunswick, 2023-08) Stairs, Chandler M.; Sacobie, Charles
Atlantic wolffish (Anarhichas lupus) became Canada's first fully marine at-risk species under the Species at Risk Act (SARA) following an 87% population decline from the late 1970s to the mid-1990s, including a 60% decrease in mature individuals. Populations on the Scotian Shelf have fallen by 65% since 1980 and continue to decline. Limited knowledge of wolffish biology hindered the identification of critical habitats under the current recovery management plan. To address this, I employed acoustic telemetry to track continuous movement, scuba surveys to observe in-situ behaviours and stable isotope analysis for trophic position estimation. I uncovered seasonal migrations linked to spawning and foraging, pair bonding, tooth replacement, den usage patterns, and egg-guarding. Trophic position assessment yielded a 3.7 value, supporting their role as keystone predators. This investigation designated Deer Island Point as a critical habitat for Atlantic wolffish and offered insight into their ecological significance in the Bay of Fundy.
Achieving a generalizable early detection of fake news
(University of New Brunswick, 2023-08) Sormeily, Asma; Ghorbani, Ali A.
In the era of widespread social media use, combatting the propagation of fake news is of paramount importance. Traditional methods for detecting fake news often struggle to adapt to evolving formats and require extensive data for early detection. To address these challenges, we propose the Multimodal Early Fake News Detection (MEFaND) approach, which leverages Graph Neural Networks (GNN) and Bidirectional Encoder Representations from Transformers (BERT). This approach enables early fake news detection using limited 5-hour propagation data and concise news content. MEFaND achieves an impressive F1-score of 0.99% (Politifact) and 0.96% (Gossipcop), outperforming existing methods. We also analyze user characteristics and study temporal and structural patterns in fake news propagation graphs. In addition, we introduce a User Susceptibility Assessment and Prediction model that employs user features to assess and predict their likelihood of spreading false information. Incorporating user actions, historical involvement, and profile traits, our model achieves 0.93% accuracy in user susceptibility assessment. This research addresses early fake news detection and user susceptibility analysis, contributing to effective strategies against misinformation on online social networks.
Knowledge retention after blended learning CPR first aid training
(University of New Brunswick, 2023-09) Sommerville, Shauna; McCloskey, Rose; Shamputa, Isdore Chola
Knowledge retention after cardiopulmonary resuscitation (CPR) first aid training delivered through blended learning is an area that has not been extensively researched. Previous research conducted has not been specific to blended learning, was limited to only CPR, and often the participants were healthcare professionals. This study employed a cross-sectional design to address this research gap by examining knowledge retention after blended learning CPR first aid training for non-healthcare professionals. Former students from two CPR first aid training companies were recruited to participate and all study data was collected using an online survey. Measures of central tendency were used to describe the data collected, while CPR first aid knowledge retention was analyzed using inferential statistics. The study findings have important implications for education delivered though blended learning, current policies for CPR first aid re-training intervals, and future research related to CPR first aid knowledge retention specifically when delivered through blended learning.