A carregar...
Publicação
Machine learning e redes sociais : automatização da análise de comentários para estratégias de marketing
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.25 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
O crescente volume de dados gerado pelos utilizadores nas redes sociais tem exigido das empresas métodos mais eficientes para a sua análise. Os sistemas tradicionais revelam limitações na interpretação de conteúdo textual, o que justifica a adoção de técnicas de Machine Learning (ML) para processar estes dados de forma automatizada. Este estudo testou um sistema de classificação automática de comentários de clientes de uma seguradora nas suas redes sociais, utilizando três algoritmos de ML - Naïve Bayes (NB), K-Nearest Neighbors (KNN) e Decision Trees (DT). Os resultados obtidos indicam que o algoritmo NB alcançou uma taxa de acerto de 65,18% na classificação de sentimentos, enquanto o KNN demonstrou melhor desempenho (85,06% de precisão) na distinção entre conteúdo gerado pela empresa e pelos utilizadores. A categorização de tags apresentou maior complexidade, com o NB a atingir 55,28% de taxa de acerto. Os resultados comprovam a viabilidade da aplicação de técnicas de ML na análise automatizada de comentários em redes sociais, oferecendo às empresas uma ferramenta valiosa para monitorizar a perceção dos clientes e orientar estratégias de marketing mais eficazes.
The increased volume of data generated by users of social networks has required companies to adopt more efficient methods of analysis. Conventional systems have been shown to have limitations in the interpretation of textual content; therefore, there has been an adoption of Machine Learning (ML) techniques to process this data in an automated way. This study evaluated a system that automatically categorises customer comments on an insurance company's social media platforms. The system employed three ML algorithms: Naïve Bayes (NB), K-Nearest Neighbours (KNN) and Decision Trees (DT). The findings demonstrate that the NB algorithm attained 65,18% accuracy in sentiment classification, while KNN exhibited superior performance (85,06% accuracy) in differentiating between content generated by the company and by users. The categorisation of tags proved to be a more complex task, with NB algorithm reaching a hit rate of 55,28%. The results demonstrate the viability of applying ML techniques for the automated analysis of comments on social networks, providing companies with a valuable tool for monitoring customer perceptions and guiding more effective marketing strategies.
The increased volume of data generated by users of social networks has required companies to adopt more efficient methods of analysis. Conventional systems have been shown to have limitations in the interpretation of textual content; therefore, there has been an adoption of Machine Learning (ML) techniques to process this data in an automated way. This study evaluated a system that automatically categorises customer comments on an insurance company's social media platforms. The system employed three ML algorithms: Naïve Bayes (NB), K-Nearest Neighbours (KNN) and Decision Trees (DT). The findings demonstrate that the NB algorithm attained 65,18% accuracy in sentiment classification, while KNN exhibited superior performance (85,06% accuracy) in differentiating between content generated by the company and by users. The categorisation of tags proved to be a more complex task, with NB algorithm reaching a hit rate of 55,28%. The results demonstrate the viability of applying ML techniques for the automated analysis of comments on social networks, providing companies with a valuable tool for monitoring customer perceptions and guiding more effective marketing strategies.
Descrição
Palavras-chave
Big data Comentários Data mining Previsão Redes sociais Comments Machine learning Forecasting Social networks
Contexto Educativo
Citação
Editora
Licença CC
Sem licença CC