Exploring text classification through the lens of Artificial Intelligence. A Comparative Analysis and Evaluation

This master's thesis aims to contribute to the field of text classification by exploring the efficiency and usefulness of various categorization methods in automating the categorization process, with a specific focus on sentiment analysis and topic classification. There is a rising need for rel...

Descripción completa

Detalles Bibliográficos
Autor: Afumatu, Alexandra-Diana
Tipo de recurso: tesis de maestría
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/399000
Acceso en línea:https://hdl.handle.net/2117/399000
Access Level:acceso abierto
Palabra clave:Natural language processing (Computer science)
Artificial intelligence
Tractament del llenguatge natural (Informàtica)
Inte
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
Descripción
Sumario:This master's thesis aims to contribute to the field of text classification by exploring the efficiency and usefulness of various categorization methods in automating the categorization process, with a specific focus on sentiment analysis and topic classification. There is a rising need for reliable and accurate text classification systems due to the exponential growth of textual data in a variety of fields. A wider range of users, including those who are not experts in Machine Learning (ML), can now use NLP technologies thanks to recent developments in the field of natural language processing (NLP). In accordance with this, the goal of this thesis is to compare and analyze the performance variations among various text categorization technologies when applied to automatically classify social media conversation, especially customer reviews for different products. By incorporating sentiment analysis and topic classification into the evaluation, this study aims to offer insights into the efficiency of various approaches in capturing the sentiment expressed in the text and identifying the underlying topics, improving the general understanding of text classification in the context of customer feedback analysis.