3830 research outputs found
Sort by
Is there a place for libraries of things in Irish public libraries?
No full textThe aim of this research study is to understand whether there is “a place for Libraries of Things in Irish public libraries”; to investigate the strategy, barriers and drivers involved in implementation of Libraries of Things (LoTs) in Ireland, and to consider whether a model for offering LoTs might be adapted to the current situation in Irish public libraries, based upon the research findings. Qualitative data for the study was gathered by interviews with 7 senior public librarians in Ireland, and a comparative interview with an American librarian. Findings suggest that there is wary support for LoTs, amongst Irish public librarians. The main concerns identified were risk, staffing, funding and space/storage. Many Irish libraries currently offer “Things”. The research shows that there is already a place for Libraries of Things in Irish public libraries, but that this is currently dependent on individual local authorities, and not an explicit national strategy
The Impact of Mobile Devices Security in Ensuring Personal Information Safety on Social Media Networks. A Case Study of Instagram
No full textThis research investigates the impact of mobile security in ensuring personal information on social media networks. A cross-sectional study was conducted to examine the role of mobile phone security measures in protecting users' personal information, particularly within the context of Instagram. Online questionnaires were administered to 119 individuals, primarily from Nigeria and Ireland, to investigate their awareness of mobile device security measures, perception of the effectiveness of Instagram's mobile security measures, and their mobile device security practices. Furthermore, a mobile device examination was conducted on an Android mobile phone to investigate the vulnerability of Instagram data stored on mobile phones to security risks in the event of unauthorised access. The findings revealed the significance of mobile security features in protecting personal information on Instagram. Generally, participants were aware of various mobile device and Instagram security features such as password protection, biometric authentication, and two-factor authentication. Participants also considered the security features offered by Instagram to be effective in safeguarding their personal information. However, there was a gap between the perceived importance and awareness of security features and behaviour aimed at safeguarding personal information. Furthermore, the mobile device examination revealed the vulnerability of personal information to security risks associated with unauthorised access. This research has implications for Instagram and its users. A user awareness module is developed to promote responsible mobile device security practices and improve personal information safety within Instagram
Enhancing Abstractive and Extractive Reviews Text Summarization using NLP and Neural Networks
No full textIn today's digital age, the exponential growth of online reviews has presented businesses with the challenge of efficiently processing huge volumes of textual data. The ability to filter valuable insights from these reviews is crucial for understanding consumer sentiments and facilitating informed decision-making. This thesis investigates the application of a Seq2Seq Long Short-Term Memory (LSTM) model for text summarization, aiming to develop an automated system capable of generating concise and informative summaries from input texts. The model underwent comprehensive training, comprising three epochs, during which it exhibited considerable progress in reducing loss and improving cosine similarity metrics, signifying its ability to learn from the dataset.
Upon evaluation, the model showcased its potential by generating summaries. However, a critical analysis revealed certain limitations in the generated summaries, notably their brevity without substantive depth and occasional lack of coherence. This highlighted the current challenges in achieving nuanced and contextually appropriate summarizations.
A comparative analysis against established models emphasized the need for further advancements. The model's deficiency in comprehensiveness and contextual relevance, particularly when faced with complex sentence structures or nuanced semantic relations, was evident.
Identified limitations encompassed the depth and complexity of summaries, reliance on a limited dataset size, and struggles with processing intricate linguistic features. To address these challenges and enhance model performance, potential avenues include dataset augmentation with diverse text samples, exploration of advanced architectures such as transformer-based models, and meticulous hyperparameter tuning.
In conclusion, while the Seq2Seq LSTM model exhibits promise for text summarization tasks, its current limitations impede the generation of comprehensive and contextually accurate summaries. The thesis underscores the necessity for future endeavors to mitigate these limitations, thereby advancing the model's capability to produce more informative and contextually apt summaries
Deciphering Deception - Detecting Fake Review using NLP by analysis of stylistic, sentiment-based, and semantic features
Get PDFThis study delves into the critical issue of identifying deceptive online reviews, a challenge increasingly prevalent in the digital marketplace. The study leverages a combination of Natural Language Processing (NLP) and Machine Learning (ML) techniques to differentiate between genuine and fraudulent reviews. The methodology encompasses stylistic analysis to assess language structure, sentiment analysis to evaluate emotional tone, and semantic analysis employing Word2Vec and Latent Dirichlet Allocation (LDA) to uncover latent topics. These components form the foundation for feature engineering for model training and evaluation.
A diverse range of machine learning models, including Random Forest, Logistic Regression, Gaussian and Multinomial Naive Bayes, Simple Neural Network, Gradient Boosted Trees, Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) with Long Short- Term Memory (LSTM), were comprehensively evaluated. The comparative analysis provides valuable insights into the performance characteristics of each model.
Notably, Logistic Regression and Simple Neural Network emerge as top contenders, presenting strong accuracy, precision, recall, and F1 score. This comparative study serves as a benchmark for future research in the domain, offering a clear understanding of the strengths and weaknesses of various machine learning approaches in addressing the deceptive online review problem, using the combination of stylistic, sentiment-based, and semantic analysis. This research not only advances the understanding of deceptive review detection but also offers a foundation for future explorations in the field of NLP and ML, aimed at enhancing the reliability and transparency of online consumer feedback
Enhacing Air Quality Index Prediction: A Comparatice Analysis of Transformer Models, Graph Neural Networks, and Traditional Approaches
No full textThis study presents a comprehensive comparative analysis of air quality index (AQI) prediction models, focusing on Transformer Models, Graph Neural Networks (GNN), and traditional approaches such as Linear Regression, Naive Bayes, and Long Short-Term Memory (LSTM). Evaluation metrics include Mean Squared Error (MSE) and Root Mean Squared Error (RMSE). Among the models, Graph Neural Networks exhibit superior performance with an MSE of 1601.86 and an RMSE of 40.02. The Hybrid Model follows closely with an MSE of 2057.53 and an RMSE of 45.36. Traditional methods like Linear Regression and Naive Bayes demonstrate moderate accuracy, while the LSTM model exhibits higher errors. Notably, the Transformer Model records the highest errors, suggesting challenges in accurately predicting AQI using this approach. These findings offer valuable insights for selecting optimal models to enhance air quality predictions in environmental research and monitoring
Factors related to employee commitment towards their roles in the Nigerian banking industry
No full textThis study investigated the factors related to employee commitment towards their roles in the Nigerian banking industry, focusing on job characteristics, organisational culture, and infrastructural support. The banking industry in Nigeria faces challenges in maintaining high levels of employee commitment, which is critical for organisational success and employee well-being. Understanding the factors influencing commitment can aid in developing strategies to enhance employee engagement and performance. A quantitative approach was employed, utilising an online Google Form survey to collect responses from employees of Access Bank Plc and Kuda Microfinance Bank. Descriptive statistical analysis and correlation testing were conducted to analyse the relationships between job characteristics, organisational culture, infrastructural support, and employee commitment. The study revealed significant findings regarding the influence of job characteristics, organisational culture, and infrastructural support on employee commitment. Clarity of job roles, meaningful work, autonomy, feedback, recognition, alignment with organisational goals, and positive organisational culture were identified as key drivers of employee commitment within the study banking organisations. Other drivers of employee commitment revealed by the study include adequate resources, technological support, training opportunities, conducive workspace, and supportive relationships. This study contributes to the existing literature by providing insights into the specific factors that influence employee commitment in the Nigerian banking sector. The findings offer practical implications for organisational leaders and HR practitioners to develop strategies aimed at improving employee engagement, satisfaction, and performance. In conclusion, this study emphasises the importance of addressing job characteristics, organisational culture, and infrastructural support to enhance employee commitment in the Nigerian banking industry. Future research directions could explore longitudinal studies, qualitative methods, and broader organisational samples to further understand and optimise employee commitment dynamics
Leveraging machine learning to predict e-commerce shopping behaviour and enhance recommendations
Get PDFThis study explored how machine learning techniques could predict e-commerce shopping behaviour and enhance product recommendations. The research analysed data from user interactions, purchase histories, and sentiment analysis to develop effective models. It involved thorough data preparation, including handling missing values, processing text with TFIDF, and applying SMOTE to balance the data. Various models were tested such as Logistic Regression, AdaBoost, Random Forest, Naive Bayes, XGBoost, and Linear Support Vector Machine. The results indicated that Logistic Regression and AdaBoost were most effective for predicting shopping behaviour while Logistic Regression and Linear Support Vector Classifier excelled in sentiment analysis. These models achieved high accuracy, precision, and recall, demonstrating their practicality for real-world e-commerce applications. Implementing these models allowed e-commerce platforms to offer personalized recommendations, enhance customer satisfaction and increase sales. This study demonstrated the significant potential of machine learning to improve e-commerce strategies and enrich the overall shopping experience
Investigating the influence of cashless transaction on customers purchasing behaviour in Nigeria.
No full textMoney is an indispensable means of making purchases. This explains why cash is still used to buy goods and services today. However, there now exists a possibility of using “cashless” money via financial technology. In turn, financial technology impose a reasonable expectation that the adoption of cashless transactions would influence customers’ purchasing behaviour because cashless transactions are faster, safer, and more reliable and convenient than traditional payment methods. Consequently, during the COVID-19 Pandemic and the Cash Crunch, Nigeria witnessed a surge in the use of cashless transactions. Therefore, this study seeks to determine whether cashless transactions influenced customers’ purchasing behaviour in Nigeria during these periods. It adopts an exploratory research design, quantitative data collection and analysis, literature analysis, and a deductive approach with a survey tool as the research strategy for data collection. The study found that the adoption of cashless transactions influences customers purchasing behaviour in Nigeria
Integrating Sentiment Analysis and Machine Learning for Robust Stock Price Prediction: A Comprehensive Study Exploring the Synergy of Sentiment Data and Historical Stock Prices for Accurate and Reliable Market Predictions
No full textThe incorporation of sentiment analysis from Twitter data into stock price prediction models for well-known electric vehicle (EV) manufacturers, such as Tesla, Ford, Nio, and Xpeng, is investigated in this study. Sentiment scores are collected from tweets using natural language processing algorithms, and they are classified as positive, neutral, or negative. Subsequently, these sentiment scores are combined with historical stock price data to train various machine learning models, such as neural network, support vector machine (SVM), decision tree, random forest, MLP Regressor and linear regression models. The accuracy of each model is evaluated using metrics like mean squared error (MSE), mean absolute error (MAE), and R-squared value. The findings demonstrate how sentiment research may improve stock price predictions, with random forest models continuously beating other models. This indicates the ability to capture hidden nonlinear relationships between sentiment and stock price. The study highlights the growing significance of sentiment analysis in financial analysis and investment decision-making, not only in the electric vehicle industry but also providing investors with important market conditions information. The results add to the expanding amount of literature on sentiment analysis applications in finance, especially in the fast-paced electric vehicle (EV) sector. These applications may enhance overall stock market efficiency and provide guidance for strategic investment choices
Navigating Identities: exploring the dynamics behind the religious and sexual identities amongst gay Latino men
No full textThroughout the last century, traditional religious values have been challenged and, matters of how these values have been used to hide prejudiced attitudes are being questioned. This study sought to extend previous findings by interviewing 5 gay Latino men and exploring the relationship between their religious and sexual identities. From the semi-structured interviews and qualitative thematic analysis of the data, 4 main themes emerged: Conflict of identities, Resolution of conflict, Compassion to self and others and Factors behind a favorable outlook on religion. The findings indicate that religion can negatively impact the journey of self-discovery of LGBTQ-identifying people, but that various strategies can help resolve this internal conflict. Participants’ responses also suggested that a more flexible religious upbringing can foster a more positive outlook on religion later in life. These findings contain important social implications as well as relevant suggestions for clinicians working with spiritual and LGBTQ-identifying individuals