Publicação
Assessing employee job satisfaction through Sentiment Analysis
| datacite.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | pt_PT |
| dc.contributor.advisor | Pinheiro, Flávio Luís Portas | |
| dc.contributor.author | Barral, Luisa Crumley | |
| dc.date.accessioned | 2024-03-12T17:14:27Z | |
| dc.date.available | 2024-03-12T17:14:27Z | |
| dc.date.issued | 2024-02-01 | |
| dc.description | Internship Report presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics | pt_PT |
| dc.description.abstract | The consulting firm seeks better insights into the satisfaction of their employees. In this way, the goal of the internship was to conduct a Sentiment Analysis study of the internal surveys answered by employees. To achieve this goal each written response was manually labeled as positive, negative or neutral and different approaches, such as lexicon-based or machine learning-based, were tested and evaluated to find the best solution in terms of performance. One issue that needed to be taken into consideration was the high imbalance between classes, large majority of the data was positive and very little was neutral or negative. This meant that extra attention needed to be paid to these cases. In terms of accuracy the best model was Random Forest, although a method using Naïve Bayes from scratch performed quite well too. It was concluded that future iterations of the project would benefit from having an aspect level classification, which could inform exactly what are the sentiments toward specific aspects contained in the text. | pt_PT |
| dc.identifier.tid | 203544102 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10362/164773 | |
| dc.language.iso | eng | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Sentiment Analysis | pt_PT |
| dc.subject | Human Resources | pt_PT |
| dc.subject | Natural Language Processing | pt_PT |
| dc.subject | Multiclass Classification | pt_PT |
| dc.subject | Supervised Learning | pt_PT |
| dc.title | Assessing employee job satisfaction through Sentiment Analysis | pt_PT |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | masterThesis | pt_PT |
| thesis.degree.name | Mestrado em Ciência de Dados e Métodos Analíticos Avançados, especialização em Métodos Analíticos para a Gestão | pt_PT |