3830 research outputs found
Sort by
Comparative study of Latent Dirichlet allocation and Louvain modularity on topic extraction from Pharma News
No full textThis research compares the efficacy of topic extraction on news content using Latent Dirichlet Allocation (LDA), a traditional method of topic extraction based on Bayesian statistics versus Louvain modularity, a graph-based algorithmic approach applied to determine clusters of words representing topics. The research explores whether the Louvain graph-based approach better captures contextual information that is lost in the LDA bag-of-words approach. The raw data is pre-processed for both methods and for the Louvain method, graph analysis techniques are further applied prior to the execution of the Louvain algorithm. Several models are produced and evaluated using topic coherence scoring and compared against manual ‘eyeballed’ topic extraction. The results show that the Louvain graph-based algorithmic approach significantly increases the topic coherence score
Are customers willing to pay companies of an existing digital service to keep their data private?
No full textData Privacy is one of the biggest issues of our time. Economically, the Big Data market have never been stronger and worth billions.
Politically, the use of citizens data, from online and off-line sources are used to create a mass-surveillance in some countries, reducing freedoms and many liberties in the name of security. Ethically, companies and third party had never collected more data from consumers, especially since the arrival of the Internet of Things. As technologies evolves and as whistleblowers expose the numerous scandals on the topic, consumers are starting to realize the outcomes of such practices. But how can they protect themselves? Legislations such as GDPR, LDPR or the California’s Online Privacy Protection Act have emerged, but it has been found that it is still not enough.
This research expose if consumers would be willing to pay companies of an existing digital service to keep their data private
Exploring burden, psychological wellbeing and life-satisfaction of carers of young adults with mental illness
No full textThe current study aimed to extend the research of caregivers’ burden in regards to carers of young adults suffering from mental illness. The main hypotheses explored how the level of burden correlated with the carers’ life satisfaction (LS) and psychological wellbeing (PWB). Additionally, which factor of burden was the greatest predictor of PWB. Other demographic variables are analysed in exploratory research section.
Online surveys containing the life satisfaction scale, psychological wellbeing scale and Zarit burden interview were used (n=72).
Analyse found significant negative correlations between burden and LS (H1) and a positive correlation between burden and PWB (H2). It also found that factor 2- social restriction impacted burden levels the most (H3). This research highlights the need to support caregivers, particularly in terms of rest bite, to improve their own mental health, thus improving the young person’s prognosis. Longitudinal studies investigating carer’s mental health over time is recommended for further research
A web app for predicting voluntary employee attrition using R Shiny & Rstudio
No full textKnowledge is one of the most critical resources that an organisation can possess. However, knowledge only constitutes an asset when it is shared and utilised effectively by firms. This capstone project shows how web applications, such as the R Shiny App, can assist the Human Resource (HR) function apply knowledge and insights from data mining to guide HR initiatives/programmes that can potentially mitigate attrition. Six supervised machine learning (ML) algorithms were applied to the IBM HR dataset to identify the determinants of, and predict, voluntary employee attrition, using R Shiny.
Internal work-related factors such as working overtime, business travel and delayed promotional opportunities were identified as negative determinants of employee attrition. In contrast, behavioural dimensions of Human Capital (HC) were found to be positive determinants of employee attrition. The results showed that the best performing algorithm based on balanced accuracy score was Logistic Regression (AUC = 0.7573). However, Naïve Bayes performed best on the sensitivity metric (Sensitivity = 0.86) while the Decision Tree model achieved the highest specificity score (Specificity = 0.8607). These findings strongly suggested that the choice of ML model for predicting voluntary employee attrition should be guided by a firm’s HR retention strategy (if one such exists) and cost-benefit implications
An investigation into the existence and structure of Irish public art museums’ online collections
No full textThis dissertation aimed to examine public art museums and galleries online collections that are available to the public and the quality of those collections. The research was completed using an online survey, sent to public art museums and galleries in the Republic of Ireland. Sampling was unnecessary due to the size of the population. The survey contained questions relating to online collections and their structure. Opinion on issues relating to collections and the impact of Covid-19 on online services were also surveyed. It was found that a slightly greater amount of the museums surveyed did not have an online collection. The greatest problems found in maintaining and creating were a lack of funding, staffing, and training. These issues are leading to a low level of online collections and a huge variation in the quality of their designs. Despite these issues, it was found that there is still a high priority and interest in creating an online collection for Irish public art museums
Understanding the spread of coronavirus (COVID-19) In ireland using S-I-R model and logistic growth function
No full textThe novel coronavirus, formerly called 2019-nCoV, or SARS-CoV-2 by ICTV (severe acute
respiratory syndrome coronavirus2, by the International Committee on Taxonomy of Viruses)
caused an outbreak of atypical pneumonia, now officially called COVID-19 by WHO (World
Health Organization) first in Wuhan, the capital city of Hubei province in December, 2019
and then rapidly spread out in the whole country of China [1].
This research aims at exploring the propagation of COVID-19 using S-I-R model and
the mathematical Logistic Growth Function and to understand the spread and propagation
of COVID-19 in Ireland, from the date of the outbreak, i.e. 29th of February 2020 [2]. The
purpose of this research is to analyse the propagation of COVID-19 in Ireland and Sweden
through the compartmental S-I-R model and to forecast the same using a general growth
model based the Logistic Growth Fuction, as it varies over a period
Craft beer sector analysis in Catalonia through an economic-financial assessment of nine leading companies
No full textThe growth of the artisan beer sector in Catalonia has been following a promising trend for some years now. It has already managed to gain almost 2% of the market share of the brewing sector and the forecast is that it will continue to grow at an incredible rate. This study aims to study the 9 leading companies in the sector to see if they follow the same pattern and, thus, to predict whether the strategy of each of the companies is similar or not. The financial study of these companies aims to analyse whether they are following a joint path and by means of an analysis of Porter's 5 forces, the external environment of the sector will be studied. In this way, we will have both internal sector and external information. With such information, it will be possible to diagnose whether the Catalan beer sector is being threatened by the artisan sector. The last objective derived from the study is to analyse whether the modern theories of capital structures are useful for local and small companies or not, which is what the financial performance of the companies under study will be studied with
Brand followers’ motivations on social media: a comparative analysis across Twitter, Facebook, and Instagram
No full text2.5 billion people use Social Media (SM) worldwide (Meshi et al. 2019); 4 in 10 internet users say they follow their favourite brands on Social Media Platforms (SMPs) (Smith, 2020). This research investigates SM users’ primary motivations for following brand-pages on three of top 3 SMPs today: Twitter, Facebook, and Instagram. Through reviewing recent literature, 10 key motivations for brand-following on SM were identified. By surveying 18-44-year-old SM users, these motivations’ relevance and weightings are investigated for brand-following on Twitter, Facebook, and Instagram. Whether the weighting of these motivations change across these platforms is also examined. Different SMPs ‘own’ different motivations in their communications. The extent to which these owned motivations aligns with users’ motivations for brand-following on that platform, is explored. ‘Relationship Maintenance, ‘Information’, ‘Brand Affiliation’, ‘Opportunity Seeking’, ‘Convenience’, ‘Inspiration’, ‘Conversation’, and ‘Entertainment’ were relevant across the 3 platforms. Significant differences in motivations’ prominence, between at least 2 of the 3 SMPs, were found for 7 of these motivations. The study’s findings are discussed, providing insights for marketers and advertisers to enhance brands’ communication’s relevancy and efficiency on SMPs
Challenges and benefits of software-as-a-service adoption for the technical support function within a software organization
No full textSoftware-as-a-Service (SaaS) model adoption by software vendors for their products delivery has been a growing trend in the technology sector. Given the limited research in the area, this exploratory study aimed to elucidate the implications of SaaS adoption for the vendor’s Technical Support function in particular, through a review of pertinent literature and practical research. The latter involved employing qualitative case study research design, conducting semi-structured interviews with relevant personnel from a software organization, and a subsequent thematic analysis of the resultant empirical data. The findings from this inquiry revealed the disruptive character of SaaS transition with its numerous and multi-faceted challenges and benefits for the department as well as its influence on the software vendor’s business model and ecosystem. This work concluded that the move to SaaS required careful consideration and recommended appropriate preparation and corrective measures to take
Predictive analysis using machine learning to predict short-term traffic
No full textAs the day begins everyone living anywhere near a busy city or working in a commercial environment gets up to travel for work. On weekends people get their vehicles out to take a family picnic or just a road trip. Checking the weather is the first thing that comes to mind if one is planning to have a good day and avoiding surprises. Similarly, it would be great to have a system where one can check what would be the traffic forecast for the next day, or the next hour. This paper intends to provide a starting point and a basic model for forecasting of traffic from day to day. Along with the forecasting, it presents a graphical representation for the user as to how the traffic conditions might be at a given location of the user’s choice. This paper aims to provide multiple forecasts with the rating of each one indicating which one would be a better option than the other. Three basic time-series forecasting models are used viz., Random Walk model, ETS (Exponential Smoothening) model and ARIMA (Autoregressive Integrated Moving Average) model. The data source is an open data provided by Transport Infrastructure Ireland (TII). The given data is transformed before being fed to the forecasting model. The R Shiny application is created to provide user interface for allowing user to select a location