Publication Search

The development of social media platforms like TikTok has created new spaces for digital economic activities, including the practive of thrifting, which has now become a trend among the public. However, government policies that block these activities have sparked various public reactions. This study aims to analyze public sentiment regarding the issue of thrifting bans on the TikTok platform using the Bidirectional Long Short-Term Memory (Bi-LSTM) method. This method was chosen because it can understand text context from both directions, allowing it to capture deeper semantic meaning. The dataset consist of 4,000 TikTok user comments collected through a crawling process. The research stages include data preprocessing, sentiment labeling, splitting training and test data, training the Bi-LSTM model, and evaluating performance using accuracy, precision, recall, and F1-score metrics. The research results show that the Bi-LSTM model achieved an accuracy of 86.15%, with stable classification performance and minimal error rate. These findings indicate that Bi-LSTM is effective for sentiment analysis of public opinions on Indonesian language social media, particularly on context specific policy issues. Further development can be carried out by adding pre-trained embeddings or attention mechanisms to improve the model’s performance.

Automatic Speech Recognition (ASR) for the Indonesian language faces significant challenges due to high Word Error Rate (WER), especially when using pre-trained models without fine-tuning. This study develops an optimized ASR system using a hybrid cloud architecture that integrates the Faster-Whisper large-v3 engine with advanced audio preprocessing techniques. The system adopts a distributed architecture, with Google Colab (Tesla T4, 15GB VRAM) as the GPU server and Ubuntu 22.04 LTS (8 core, 32GB RAM) as the client. Evaluation was conducted on five Indonesian audio samples covering formal news, informal conversations, and long-duration recordings. The system achieved an 80% success rate in processing, with WER ranging from 27.69% (formal news) to 645.16% (informal conversations). Resource utilization was also efficient, with 21.3% GPU usage and 35.4% RAM usage. Processing time remained stable for normal-sized files but experienced timeouts on large files (>50MB). The results indicate that hybrid cloud architecture is feasible for distributed ASR processing in Indonesian, with several areas still open for optimization toward production deployment.

Typing errors in documents are fairly common. The process of checking typing errors manually will take a lot of time. Therefore, a system called Indonesian spelling correcting with Jaro Winkler is needed. Spelling Correcting is a feature that can check and correct word writing errors automatically. Jaro Winkler is an algorithm used for the word correction process by calculating the value obtained from the results of the operation of modifying one word with another word with the help of a matrix. Based on the results of trials on 13 words, namely "Alaman Amus Seperti Pada Gamba Tersebut Digunakan Untuk Memasukkan Data Kata Pada KBBI ", this spelling correcting application can produce 3 correct word corrections to " halaman kamus seperti pada gambar tersebut digunakan untuk data pada kbbi ", each Word improvement is calculated using the Jaro Winkler formula, getting a score above 0.94 for each word tested.

The global economic recession is a global economic downturn that affects the domestic economies of countries in the world. The stronger the economic dependence of one country on the global economy, the faster a recession will occur in that country. In 2020 the country of Indonesia and even the world are exposed to the COVID-19 virus which has an impact on the country's economic growth, even the world economy. This is the trigger for an economic recession. This has led to many different public perspectives on the occurrence of a global economic recession whose opinions or reactions are expressed on social media Youtube. The data was obtained by crawling techniques from social media Youtube with a total of 500 comments used. The data is then labeled (class) with a lexicon-based method with an Indonesian language dictionary. From the labeling results, it was obtained 185 positive labeled data (37%) and 315 negative opinions (63%). The data preprocessing stage is carried out in preparation for the data to be processed for sentiment analysis. Of the many opinions obtained, an analysis of public sentiment regarding the 2023 global economic recession will be carried out using the Naïve Bayes classification algorithm. This study also applied the TF-IDF word weighting method with the n-gram feature used, namely bigram (n=1). The system will be evaluated using a confusion matrix. The implementation results show a prediction model with a total of 500 opinion data with a comparison of training data and test data of 9:1, producing an accuracy value of 84.00%, a precision value of 75.00%, a recall of 30.00%, and an f1-score of 42.86%. The performance of the system model built in this study can be said to be good.