3830 research outputs found
Sort by
Comparative Analysis of Traditional and Large Language Model Techniques For Multi-Class Emotion Detection
No full textIn recent years, YouTube's comment sections have drawn interest in analyzing the emotions within them. This study investigates the emotion detection of YouTube comments, seeking to improve accuracy by testing machine learning and deep learning models. We compare traditional models - Logistic Regression, Naive Bayes, Decision Trees, Support Vector Machines, Random Forests, and newer deep learning models like - LSTMs, BERT, and DistilBERT. Recent deep learning advancements have shown promise for emotion detection. We aim to determine the most effective approaches.Although traditional models offered insightful categorizations, deep learning structures like LSTM and DistilBERT displayed remarkable capabilities, indicating their potential for very accurate emotion detection. These results give key understandings of choosing models based on specific needs, highlighting the necessity for ongoing improvement and optimization, especially in deep learning methods, to reach greater precision and durability in the classification of emotions within YouTube video comments
Securenet: Safeguarding Networks on The AWS Cloud Platform
No full textIn today's fast-paced environment, cybersecurity is a top priority for organizations. With the advancement of technology and the proliferation of network threats, improving network security has become a priority. This work addresses Network Security as a Service (NSaaS) on cloud platforms and specifically its role in protecting critical systems and sensitive data. The goal is to evaluate the effectiveness of NSaaS in providing good security. NSaaS leverages the cloud while implementing best-in-class security measures to combat cyberattacks. This study evaluates the NSaaS performance of Amazon Web Services (AWS) through qualitative testing, analysis, and data analysis. Penetration analysis, attack analysis, network analysis and finally security measures are performed, revealing the ability of NSaaS to enhance
cloud-based security by identifying and preventing various threats.
This research demonstrates the value of NSaaS in improving cloud security. This is a simple solution that follows cloud computing principles. By providing valuable information, this research can help organizations improve their cybersecurity policies in today's dynamic environment
An Ensemble Learning Approach for Improved Loan Fraud Detection: Comparing and Combining Machine Learning Models
No full textThis thesis investigated loan fraud detection using advanced machine learning techniques, focusing on Logistic Regression, Random Forest, AdaBoost, Long Short-Term Memory (LSTM) networks, and Convolutional Neural Networks (CNN). The study emphasized the importance of feature selection, and explored forward, backward, and automatic methods to improve model performance. Comparative analysis across models revealed that Random Forest consistently outperforms other models in accuracy and efficiency, regardless of the feature selection technique. AdaBoost showed consistent results but at a higher computational cost, while LSTM and CNN were highly sensitive to the choice of feature selection, affecting their performance significantly. The thesis concluded that feature selection was vital for optimizing machine learning models for fraud detection, with the impact varying significantly across different algorithms. Random Forest emerged as a robust and efficient model for fraud detection, adaptable to various applications. The findings underscored the potential of machine learning to strengthen financial security and trust
A feedback system for e-commerce business from customer reviews using aspect-based sentiment analysis
No full textIn the contemporary business landscape, understanding customer sentiment is paramount for the success of new enterprises. This research project aims to develop a sophisticated feedback system utilizing aspect-based sentiment analysis (ABSA) of customer reviews. By dissecting customer feedback into specific aspects and analysing the sentiment associated with each, businesses can gain granular insights into customer experiences. This system will empower new businesses to make data-driven decisions, improve products and services, and ultimately enhance customer satisfaction and loyalty. The study used the customer reviews extracted from Amazon for several products from different sub-categories of women’s footwear which were rigorously pre-processed. The aspects were identified using Term Frequency Inverse Document Frequency. The reviews were labelled with sentiments for the aspects using OPE GPT-3.5 turbo. The pre-trained models of Microsoft’s DeBertaV3 and Google’s Flan-T5 were used to evaluate their performance against GPT 3.5. Both the models performed moderately
Interpretable machine learning for customer churn prediction
No full textThis study aims to develop and evaluate interpretable machine learning models for predicting customer churn in the telecommunications sector. The dataset, consisting of 7,043 customer records and 21 features, was preprocessed to handle missing values, encode categorical variables, and balance the target class using SMOTE. Five machine learning models were implemented: Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and Neural Network. The Gradient Boosting model emerged as the most effective, providing a balanced combination of accuracy and interpretability. Partial Dependence Plots (PDPs) and Local Interpretable Model-agnostic Explanations (LIME) were used to explain the model’s predictions, revealing that contract type, monthly charges, and online security services were significant predictors of churn. The results suggest that targeted interventions based on these factors could significantly reduce churn, thereby improving customer retention and business profitability
The perceptions of open educational resources by teaching staff in higher education in Ireland
No full textThe aim of this study was to evaluate the impact of Emergency Remote Learning on the perceptions of Open Educational Resources. This was achieved by comparing the perspectives of academic teaching staff in this research with those documented in pre-COVID-19 studies. A total of 105 participants from 16 institutions in Ireland were surveyed using a combination of quantitative and qualitative questions. The findings indicate that the shift to Emergency Remote Learning has not significantly diminished the perceived barriers to Open Educational Resources. Instead, it has brought forward fresh concerns about the implications of Open Education on conventional teaching methods. Although a national policy would grant individual institutions the autonomy to devise courses in line with their mission and strategy, the outcomes of this study highlight the need for practical assistance, training, and guidance at an institutional level
A literature review on high-functioning autistic employees
Get PDFThis literature review aims to contribute to the field of autism and employment. It will analyse bibliographic data on peer-reviewed research on the benefits and challenges of a neurodiverse workforce. Similarly, it will examine the experiences of high-functioning autistic people in the workplace. Despite reports in popular media on the benefits of a neurodiverse workplace, including better innovation and company performance – there is very little academic research to support these claims. Of the limited existing literature, there are very few articles in business and management journals. This review gathers empirical evidence to test such claims. The research is based on high-functioning autistic people (verbal, with average or above IQ). Autism will be referred to as Autism Spectrum Disorder (ASD) from here on, which includes Asperger syndrome under the criteria of the DSM-5.
Data from peer-reviewed research articles on high-functioning autism, employment and adults in the Social Sciences Citation Index were analysed to gauge the current trends in publication and citation. This database was chosen to limit the medical literature, which is extensive and an entirely different field. The data indicates that research on the experiences autistic employees, and their employers, up to recent years has been an understudied field. Based on the analysis used for this study, research and interest in this field began to emerge in publications in 2005. This review identified high-functioning autism as an increasingly important factor to consider in designing hiring and recruitment processes. It is also a significant consideration in conflict-resolution, communication and the training and support areas of management. Considering the steep increase in autism diagnoses over the past 30 years, coupled with the supports made available to autistic people up to third-level education; a more neurodivergent, educated talent pool is emerging which will change the way managers approach and manage diversity in the workplace
True crime consumption predicts biological sex and culture’s wellbeing: interlinking defensive behaviour and perceived victimisation
No full textThis study sought to ascertain whether consuming true crime indirectly impacts wellbeing, through interlinking a motive for consuming true crime, being to learn defensive techniques, with subsequent perceived victimisation and whether results are specific to biological sex and/or culture. The type of platforms used to access and consume true crime, association with wellbeing will be explored. A quantitative, between groups design with cross sectional and correlational statistical tests investigated 88 participants who were 18 year or older. Individuals participated in an anonymous survey. The interlink between consuming true crime and wellbeing was unfulfilled, however, defensive behaviour frequency predicting perceived victimisation was statistically significant. Consumption of true crime and overall wellbeing significantly differed based on the type of platform used to access true crime. Even though the interlink between true crime and wellbeing was unfulfilled, interlinking defensive behaviour and perceived victimisation strengthens the argument to challenge Irelands ban on defensive tools
A quantitative study on adopting robotic process automation as a technology tool in the manufacturing enterprises of Ireland
No full textThe main aim of this study is to examine the UTAUT factors affecting Individuals' Behavioral Intentions to adopt RPA Technology and user behavior in the Manufacturing Enterprises of Ireland. This research was quantitative, and Questionnaires were used throughout the study to collect information from participants. The study's target audience was 150 employees in the manufacturing business who understand how to use Robotic Process Automation (RPA) to streamline labor-intensive production activities. The participants were selected based on the convenience sampling technique. The statistical analysis application SPSS was used to analyze the data for the investigation. The results indicated that there was a significant impact of performance expectancy, facilitating conditions on Individuals' Behavioral Intentions to adopt RPA Technology, social influence, and effort expectancy on Individuals' Behavioral Intentions to adopt RPA Technology, and there was also a significant relationship between Individuals' Behavioral Intentions to adopt RPA Technology and user behavior.This study guides future researchers on various approaches to identify the key aspects to consider while implementing and utilizing RPA technology
The influence of performance appraisals on employee retention within the hospitality sector in Ireland
No full textThe aim of this study was to understand the influence of performance appraisals on employee retention within the Irish hospitality sector. The Irish hospitality sector has long faced a challenge of both recruiting people to the sector, as well as retaining these valuable employees. This study aimed to bridge the empirical gap between the previous literature, with the objective of conducting semi-structured interviews with employees in this sector. Semi structured interviews were carried out with employees from the Irish hospitality sector, in order to understand their views on performance appraisals and if this process could contribute to their commitment to an organisation. The Transformational Leadership Framework was used in order to develop interview questions and data collected was analysed using a branch of Thematic Analysis, known as Template Analysis. The results confirmed that performance appraisals can influence an employee’s commitment to an organisation, through the importance of communication, feedback, employee engagement, motivation and employees’ relationship with managers. The results demonstrate that performance appraisals influence commitment and in turn, employee retention levels within the sector. On foot of these results, it was concluded that businesses within the Irish hospitality sector could use this as a foundation to inform their current and/or future performance management methods, in order to positively affect retention rates and retain valued employees within the sector