Skripsi
ANALISIS SENTIMEN OPINI PUBLIK MENGENAI HARGA MINYAK BBM DAN MINYAK GORENG PADA TWITTER MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN)
The rapid growth of social media has made it easier for people to express their opinions on online platforms such as blogs, web forums, and social media platforms like Instagram, Facebook, and Twitter. Information and comments spread on Twitter encompass various types, including positive, negative, and neutral remarks. Currently, extensive research has been conducted in the field of Natural Language Processing (NLP), specifically focusing on sentiment analysis. Based on this, a software tool has been developed to predict sentiment analysis using the Convolutional Neural Network (CNN) method. The dataset used in this research consists of tweets related to the topic of rising cooking oil and fuel prices from July 27, 2022, to August 18, 2022, totaling 601 tweets. The data was processed into four variations of datasets, based on data splitting ratios of 70:30 and 60:40, and different pre-processing stages, either through all Pre-Processing processes or only through tokenizing.The research results indicate that the model trained using data with a 70:30 data splitting scheme and undergoing full Pre-Processing has the best performance, with an accuracy value of 0.63055, precision of 0.57934, recall of 0.68477, and F1-Score of 0.55286.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307005300 | T122532 | T1225322023 | Central Library (REFERENS) | Available but not for loan - Not for Loan |
No other version available