%0 Journal Article %1 pipin2023sentiment %A Pipin, Sio Jurnalis %A Sinaga, Frans Mikael %A Winardi, Sunaryo %A Hakim, Muhammad Noor %D 2023 %J JURNAL MEDIA INFORMATIKA BUDIDARMA %K Analysis ChatGPT Data Deep Fast Learning R-CNN Sentiment Twitter myown %N 4 %P 2137-2148 %R http://dx.doi.org/10.30865/mib.v7i4.6816 %T Sentiment Analysis Classification of ChatGPT on Twitter Big Data in Indonesia Using Fast R-CNN %U https://ejurnal.stmik-budidarma.ac.id/index.php/mib/article/view/6816 %V 7 %X The advent of OpenAI's ChatGPT, a large language model (LLM) proficient in various fields including artificial intelligence (AI) and natural language processing (NLP), has ignited a plethora of opinions and discussions, especially on social media platforms like Twitter in Indonesia. This research seeks to delve into the intricate dynamics of these discussions, aiming to map both the commendations and criticisms surrounding ChatGPT's technological advancements and potential negative impacts. Utilizing deep learning-based sentiment analysis techniques, the study employs Convolutional Neural Network (CNN) and Fast Region-based Convolutional Network (Fast R-CNN) to analyze a dataset consisting of 7,604 tweets categorized into "Positive", "Negative", and "Neutral" sentiments. The objective is to provide a comprehensive understanding of the societal perceptions towards this artificial intelligence technology in the Indonesian context. The methodology encompasses several stages including data collection from Twitter, data cleaning, and pre-processing, followed by the application of CNN and Fast R-CNN models for sentiment analysis. The findings indicate a superior performance of the Fast R-CNN model, achieving an accuracy rate of 94.5%, compared to the CNN model with an accuracy rate of 86%. In conclusion, the research highlights the effectiveness of integrating Fast R-CNN in sentiment analysis to extract deeper insights from Twitter data in Indonesia. This study not only contributes to the scientific literature in the fields of sentiment analysis and natural language processing but also aids in formulating informed strategies to navigate the challenges and opportunities presented by artificial intelligence technology in the Indonesian landscape. Future research avenues should focus on optimizing this sentiment analysis model and exploring other potential applications of this technology in the dynamically evolving digital landscape in Indonesia.

@article{pipin2023sentiment, abstract = {The advent of OpenAI's ChatGPT, a large language model (LLM) proficient in various fields including artificial intelligence (AI) and natural language processing (NLP), has ignited a plethora of opinions and discussions, especially on social media platforms like Twitter in Indonesia. This research seeks to delve into the intricate dynamics of these discussions, aiming to map both the commendations and criticisms surrounding ChatGPT's technological advancements and potential negative impacts. Utilizing deep learning-based sentiment analysis techniques, the study employs Convolutional Neural Network (CNN) and Fast Region-based Convolutional Network (Fast R-CNN) to analyze a dataset consisting of 7,604 tweets categorized into "Positive", "Negative", and "Neutral" sentiments. The objective is to provide a comprehensive understanding of the societal perceptions towards this artificial intelligence technology in the Indonesian context. The methodology encompasses several stages including data collection from Twitter, data cleaning, and pre-processing, followed by the application of CNN and Fast R-CNN models for sentiment analysis. The findings indicate a superior performance of the Fast R-CNN model, achieving an accuracy rate of 94.5%, compared to the CNN model with an accuracy rate of 86%. In conclusion, the research highlights the effectiveness of integrating Fast R-CNN in sentiment analysis to extract deeper insights from Twitter data in Indonesia. This study not only contributes to the scientific literature in the fields of sentiment analysis and natural language processing but also aids in formulating informed strategies to navigate the challenges and opportunities presented by artificial intelligence technology in the Indonesian landscape. Future research avenues should focus on optimizing this sentiment analysis model and exploring other potential applications of this technology in the dynamically evolving digital landscape in Indonesia.}, added-at = {2024-03-23T16:47:05.000+0100}, author = {Pipin, Sio Jurnalis and Sinaga, Frans Mikael and Winardi, Sunaryo and Hakim, Muhammad Noor}, biburl = {https://www.bibsonomy.org/bibtex/200fcab03c7ff557f2862d2506899cf98/siopipin}, doi = {http://dx.doi.org/10.30865/mib.v7i4.6816}, interhash = {c1ea75180e96636542041c19c5b07ad6}, intrahash = {00fcab03c7ff557f2862d2506899cf98}, journal = {JURNAL MEDIA INFORMATIKA BUDIDARMA}, keywords = {Analysis ChatGPT Data Deep Fast Learning R-CNN Sentiment Twitter myown}, number = 4, pages = {2137-2148}, timestamp = {2024-03-23T16:47:05.000+0100}, title = {Sentiment Analysis Classification of ChatGPT on Twitter Big Data in Indonesia Using Fast R-CNN}, url = {https://ejurnal.stmik-budidarma.ac.id/index.php/mib/article/view/6816}, volume = 7, year = 2023 }