Predicting the number of likes on Instagram with TensorFlow

1 billion people use Instagram every month, which makes it one of the most popular social networks worldwide. Currently, there is an enormous scope market with the potential to be optimized to increase Instagram posts popularity and engagement. In this project, the main goal is to predict the number...

Descripción completa

Detalles Bibliográficos
Autor: Cantero Priego, Joel
Tipo de recurso: tesis de maestría
Fecha de publicación:2020
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:2117/339937
Acceso en línea:https://hdl.handle.net/2117/339937
Access Level:acceso abierto
Palabra clave:Machine learning
Social networks
Neural networks (Computer science)
Natural language processing (Computer science)
tensorflow
data science
deep learning
machine learning
convolutional neural networks
natural language processing
instagram
keras
data augmentation
Aprenentatge automàtic
Xarxes socials
Xarxes neuronals (Informàtica)
processament del llenguatge natura
Tractament del llenguatge natural (Informàtica)
Àrees temàtiques de la UPC::Informàtica
Descripción
Sumario:1 billion people use Instagram every month, which makes it one of the most popular social networks worldwide. Currently, there is an enormous scope market with the potential to be optimized to increase Instagram posts popularity and engagement. In this project, the main goal is to predict the number of likes given a post, building a deep learning model. This model will use convolutional neural networks, natural language processing and other deep learning techniques within the TensorFlow framework. The input data is composed of categorical, numerical data, as well as some image and text data.