Browse
Recent Submissions
Item Sentiment analysis on code-mixed transgender tweets and their comparison using ML, DL and BERT(UMT, Lahore, 2023) BABAR ALI KHANThe field of sentiment analysis has become a crucial area of study for comprehending public opinion and the sentiment conveyed on social networking sites platforms. The primary objective of this research is to conduct sentiment analysis on code-mixed multilingual tweets pertaining to the transgender act of 2018 in Pakistan. The aim is to obtain a deeper understanding of the prevailing public sentiment towards this notable legislative advancement. Furthermore, a comparative examination is undertaken to assess the efficacy of different machine learning and deep learning models. This evaluation involves the utilization of TF-IDF vectorization, GloVe embeddings, and multilingual BERT embedding as input features. The dataset consists of a mixture of English, Urdu, and Roman Urdu tweets, which poses distinct linguistic difficulties because of the code-mixing present in the data. In order to tackle these challenges, various machine learning models such as logistic regression (LR), naive Bayes model, along with support vector machine (SVM) were utilized. The findings indicate that the performance of TF-IDF vectorization is competitive, as it achieves significant accuracies, recall, precision, and F1 scores. Nevertheless, the application of multilingual BERT embeddings greatly improved the efficacy of logistic regression and SVM models, underscoring the significance of utilizing sophisticated language representations models for emotion analysis in code-mixed multilingual scenarios. Various deep learning models, such as recurrent neural networks (RNN), long short-term memory (LSTM), and bidirectional LSTM (Bi-LSTM), were utilized in the study. These models incorporated both GloVe embeddings and multilingual BERT embeddings. The deep learning models that integrated multilingual BERT embeddings demonstrated superior performance compared to the models that employed GloVe embeddings, achieving remarkable levels of precision, recall, accuracy, and F1 scores. The findings of this study highlight the efficacy of multi- lingual BERT embeddings in capturing subtle variations in sentiment within code-mixed multi- lingual tweets, outperforming conventional machine learning models.The comparative analysis emphasizes the benefits of utilizing deep learning models, specifically those that utilize multi- lingual BERT embeddings, in effectively capturing sentiment with precision. The enhanced efficacy of these models can be ascribed to their capacity to apprehend contextualized information and semantic associations among words, which holds significant importance in code-mixed multilingual scenarios. The results of this research make a valuable contribution to the domain of emotion analysis in code-mixed multilingual settings by offering valuable insights into the public sentiment surrounding the transgender act of 2018 in Pakistan. The comparative analysis highlights the advantages of employing deep learning models that utilize multilingual BERT embeddings. This emphasizes the significance of utilizing developed language representations models for tasks related to sentiment analysis. The implications of these findings are relevant for scholars, policymakers, and social activists involved in the field of transgender rights, as they offer a thorough comprehension of public attitudes towards the legislation.Item Use of AutoEndcoder & LSTM AutoEncoder for Real-time Anomaly Detection in Banking Transactio(UMT, Lahore, 2023) Faizan IrshadAnomaly is something that deviates from what is considered normal or expected. It can refer to a deviation from a rule or pattern, a strange or unusual occurrence, or a discrepancy in data. Anomaly detection in banking transactions involves identifying unusual or suspicious patterns in financial data including fraudulent or illegal activities, as well as potential errors or inaccuracies in the data. Banks process billions of transactions on daily basis worldwide and its practically impossible for the Banks to detect anomalies in the transactions using traditional rule based methods in real time environment. Artificial Intelligence offers a solution to this problem. We have introduced a novel approach using AutoEncoder and Long Short-Term Memory (LSTM) AutoEncoder for the detection of anomalous transaction in real life banking transactions dataset. One unique aspect of our model is also its implementation in an unsupervised manner separately for every account, allowing model to adapt to individual account behaviors and identify transactions that deviate from the norm for that particular account. Results of the unsupervised model were tested using labeled data. Our research shows that AutoEncoder outperformed LSTM AutoEncoder in terms of anomaly detection. The implementation of the proposed model on real life labelled transactions dataset has proved the effectiveness of proposed model in terms of real-time detection of anomalies in banking transactions which may be indicative of Fraud, Money laundering detection or Errors & Omissions.