Sentiment analysis of Twitter messages regarding the KFC company inthe first quarter in Latin America 2022
It was proposed to answer if the machines can really analyzethe sentiments of the tweets, then the messages in Spanish onTwitter that spoke of KFC were analyzed. The tweets werecaptured every day in the time period of the first quarter ofthe year 2022 from the Latin American region, later theywere a...
| Authors: | , , |
|---|---|
| Format: | article |
| Status: | Published version |
| Publication Date: | 2024 |
| Country: | Perú |
| Institution: | Universidad de San Martín de Porres |
| Repository: | Revistas - Universidad de San Martín de Porres |
| Language: | Spanish |
| OAI Identifier: | oai:revistas.usmp.edu.pe:article/2677 |
| Online Access: | https://portalrevistas.aulavirtualusmp.pe/index.php/rc/article/view/2677 |
| Access Level: | Open access |
| Keyword: | Sentiment analysis, Machine Learning, Deep Learning, Twitter messages Análisis de sentimientos, Aprendizaje Automático, Aprendizaje Profundo, mensajes de Twitter |
| Summary: | It was proposed to answer if the machines can really analyzethe sentiments of the tweets, then the messages in Spanish onTwitter that spoke of KFC were analyzed. The tweets werecaptured every day in the time period of the first quarter ofthe year 2022 from the Latin American region, later theywere analyzed by month and for each company mentionedin the tweets, these came to add 39,269 messages for KFC. We focused on discovering what were the feelings related to eachmessage left, for this reason the polarity of the feeling betweenpositive and negative was sought, the first being related to wellbeing,happiness, and love, while the second polarity, negativewas related to discomfort, sadness, and hatred. After obtainingthe polarity, it remained to discover what its degree was, the high,medium and low indicators were used, thus having the degrees:high positives, medium positives, low positives, high negatives,medium negatives, and low negatives. The term neutral or neutralwas used for unpolarized messages, not meaning a feeling, that is,neutral feelings do not exist, it is only the result of the absence ofsufficient data to classify it in some polarity. Everything mentionedwas done through artificial intelligence, but considering that it wassought to answer if the feelings of the text messages can really beanalyzed, that is why two different heuristics were used, MachineLearning and Deep Learning, with them it was possible identifythe polarity and degree of sentiment of Twitter messages regardingthe KFC company in the first quarter in Latin America 2022. |
|---|