ARC (Academic Research Collection) (College Dubin)
Not a member yet
359 research outputs found
Sort by
Fake News Detection using Natural Language Processing
Get PDFNowadays with the advance of technologies we have vast access to any sort of information. We are able to use our phone/computer to access the news of any part of the world. It is great to keep us informed about everything that is happening around the world. It is also a powerful tool used for companies while making strategic business decisions. The biggest issue is that technology can and is being used to manipulate people/companies by propagating fake news. Fake news can mislead people\u27s perceptions while forming opinions on a determined subject. It can also have a big impact on a company during the strategic decision-making process. Our fake news detection model will allow people/companies to identify whether the news/information is real or not. With the model, people can form opinions on any subject without being manipulated by fake news. In the same way, companies can make better market decisions based on the analyses of real news/information instead of being influenced by fake news. Our fake news detection model will use NLP (Natural Language Processing) to predict if the news is real or fake. See below for a more detailed explanation of how our model will predict the news by analysing phrase patterns
Human Resource Management
Get PDFA clock requires every single, even the smallest piece of its’ machinery to perform the tasks that is meant to do in order to function correctly. If there is a piece that is not working properly, it can be the cause of the clock not working at all. This same premise can be applied to the work environment, viewing the organization as ‘’the clock’’ and employees as ‘’the machinery’’, performing tasks for the general functionality of the organization that could lead it to either success or failure. This is the reason why it is vital for any type of organization that is willing to achieve its’ goals to make sure that every single individual working within it is performing their tasks to the best of their capacities. If the organization is not a human entity, how can it make sure that its’ workforce is complying to play their part for the success of the company? Well, the answer to this question could be Human Resource Management
Credit worthiness tool for Credit Unions
Get PDFThe core objectives for the Capstone project were to mine data in order to create a tool for Credit Unions (and banks) that will evaluate customers credit worthiness based on an ethical standardised criteria that is transparent to all. We explored why this was necessary and explored how important it could be to the business. Our focus is on helping Credit Unions have a stronger online presence as the banking sector has been changing rapidly and moving online and Credit Unions are currently behind in the market in this regard .This tool would help automate the credit approval process, reducing the underwriting time and allow customers to get answers quicker in regards to the potential of securing a line of credit. All this in just a few clicks or taps of the finger
Revised Avenues of Assessment in Higher Education in the presence of AI Generative Contents
Get PDFThis study explores the impact of Generative Artificial Intelligence (AI) tools on academic assessments, focusing on their efficacy in generating unique content across various domains. Dr. Muhammad Iqbal from CCT College Dublin emphasizes the increasing prevalence of AI generative tools and their potential influence on learning quality in academia. The study addresses concerns related to assessment standards in higher education and proposes the evaluation of AI-generated content reliability
An evaluation of the HR function within an organization and how the function contributes to providing a competitive advantage
Get PDFHuman resources management is all organizational activities concerned with recruiting, training, appraising and rewarding, directing, motivating, and controlling workers. And it can improve the workforce. This work discusses how the RH functions contribute to providing a competitive advantage. It starts with an essay about how the benefits of RH can lead to a competitive advantage. Then brings a recommendation regarding staff requirements and an organizational structure for the owner of Motorway Services
An assessment of the effectiveness of using data analytics to predict death claim seasonality and protection policy review lapses in a life insurance company
Get PDFData analytics tools are becoming increasingly common in the life insurance industry. This research considers two use cases for predictive analytics in a life insurance company based in Ireland. The first case study relates to the use of time series models to forecast the seasonality of death claim notifications. The baseline model predicted no seasonal variation in death claim notifications over a calendar year. This reflects the life insurance company’s current approach, whereby it is assumed that claims are notified linearly over a calendar year. More accurate forecasting of death claims seasonality would enhance the life insurance company’s cashflow planning and analysis of financial results. The performance of five time series models was compared against the baseline model. The time series models included a simple historical average model, a classical SARIMA model, the Random Forest Regressor and Prophet machine learning models and the LSTM deep learning model. The models were trained on both the life insurance company’s historical death claims data and on Irish population deaths data for the 25-74 age cohort over the same observation periods. The results demonstrated that machine learning time series models were generally more effective than the baseline model in forecasting death claim seasonality. It was also demonstrated that models trained on both Irish population deaths and the life insurance company’s historical death claims could outperform the baseline model. The best forecaster was Facebook’s Prophet model, trained on the life insurance company’s claims data. Each of the models trained on Irish population deaths data outperformed the baseline model. The SARIMA and LSTM consistently underperformed the baseline model when both were trained on death claims data. All models performed better when claims directly related to Covid-19 were removed from the testing data. The second case study relates to the use of classification models to predict protection policy lapse behaviour following a policy review. The life insurance company currently has no method of predicting individual policy lapses, hence the baseline model assumed that all policies had an equal probability of lapsing. More accurate prediction of policy review lapse outcomes would enhance the life insurance company’s profit forecasting ability. It would also provide the company with the opportunity to potentially reduce lapse rates at policy review by tailoring alternative options for certain groups of policyholders. The performance of 12 classification models was assessed against the baseline model - KNN, Naïve Bayes, Support Vector Machine, Decision Tree, Random Forest, Extra Trees, XGBoost, LightGBM, AdaBoost and Multi-Layer Perceptron (MLP). To address class imbalance in the data, 11 rebalancing techniques were assessed. These included cost-sensitive algorithms (Class Weight Balancing), oversampling (Random Oversampling, ADASYN, SMOTE, Borderline SMOTE), undersampling (Random Undersampling, and Near Miss versions 1 to 3) as well as a combination of oversampling and undersampling (SMOTETomek and SMOTEENN). When combined with rebalancing methods, the predictive capacity of the classification models outperformed the baseline model in almost every case. However, results varied by train/test split and by evaluation metric. Oversampling models performed best on F1 Score and ROC-AUC while SMOTEENN and the undersampling models generated the highest levels of Recall. The top F1 Score was generated by the Naïve Bayes model when combined with SMOTE. The MLP model generated the highest ROC-AUC when combined with BorderlineSMOTE. The results of both case studies demonstrate that data analytics techniques can enhance a life insurance company’s predictive toolkit. It is recommended that further opportunities to enhance the predictive ability of the time series and classification models be explored
Unlocking the Pragmatics of Emoji: Evaluation of the Integration of Pragmatic Markers for Sarcasm Detection
Get PDFEmojis have become an integral element of online communications, serving as a powerful, under-utilised resource for enhancing pragmatic understanding in NLP. Previous works have highlighted their potential for improvement of more complex tasks such as the identification of figurative literary devices including sarcasm due to their role in conveying tone within text. However present state-of-the-art does not include the consideration of emoji or adequately address sarcastic markers such as sentiment incongruence. This work aims to integrate these concepts to generate more robust solutions for sarcasm detection leveraging enhanced pragmatic features from both emoji and text tokens. This was achieved by establishing methodologies for sentiment feature extraction from emojis and a depth statistical evaluation of the features which characterise sarcastic text on Twitter. Current convention for generation of training data which implements weak-labelling using hashtags or keywords was evaluated against a human-annotated baseline; postulated validity concerns were verified where statistical evaluation found the content features deviated significantly from the baseline, highlighting potential validity concerns for many prominent works on the topic to date. Organic labelled sarcastic tweets containing emojis were crowd sourced by means of a survey to ensure valid outcomes for the sarcasm detection model. Given an established importance of both semantic and sentiment information, a novel sentiment-aware attention mechanism was constructed to enhance pattern recognition, balancing core features of sarcastic text: sentiment incongruence and context. This work establishes a framework for emoji feature extraction; a key roadblock cited in literature for their use in NLP tasks. The proposed sarcasm detection pipeline successfully facilitates the task using a GRU neural network with sentiment-aware attention, at an accuracy of 73% and promising indications regarding model robustness as part of a framework which is easily scalable for the inclusion of any future emojis released. Both enhanced sentiment information to supplement context in addition to consideration of the emoji were found to improve outcomes for the task
Recurrent Neural Networks for Flash GDP Estimates in Ireland: A Comparison with Traditional Econometric Methods
Get PDFGDP is the single most important barometer for the health of an economy. It’s an important input into the decision making processes of government, industry and state institutions such as central banks. To be useful as an indicator, GDP estimates need to be both timely and accurate. To meet the needs of users, many national statistical institutes publish early or flash estimates of GDP which are produced within 30 days after the end of a quarter. Given the long lags involved in the data collection processes which feed into GDP estimates, these flash estimates are often largely model based. Within the EU, the models utilised are typically the workhorse models of statistics and time series econometrics such as regression and ARIMA models. This study seeks to assess whether deep learning approaches can be used to improve the accuracy of early estimates in a flash GDP context. To assess this a number of number of LSTM models were trained with extensive hyperparameter tuning with their accuracy evaluated based on common metrics along with walk forward validation on a test set. These results were compared to a similar approach with time series econometric models such as ARIMA, ARIMA with additional explanatory variables and VAR. The study concludes that ARIMA models with explanatory variables provide the most accurate estimates. The study also provides recommendations for the improvement of Ireland’s flash GDP estimates process. The study recommends the use of additional explanatory variables in the context of ARIMA modelling. This recommendation was based on findings from this study and insights into Ireland’s flash estimate processes gained from in-depth interviews with experts