Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Cyberspace: Jurnal Pendidikan Teknologi Informasi IJID (International Journal on Informatics for Development)
Kiftiyani, Usfita
Unknown Affiliation
Computer Science & IT Education Other

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Veil and Hijab: Twitter Sentiment Analysis Perspective Lestari, Lusiana; R Wahyudi, M Didik; Kiftiyani, Usfita
IJID (International Journal on Informatics for Development) Vol. 9 No. 1 (2020): IJID June
Publisher : Faculty of Science and Technology, UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2020.09108

Abstract

Controversies about veil and hijab are often occur in society. Especially in today’s digital era, public opinion expressed through social media can greatly influence the others opinions, regardless of whether it is positive or negative. Therefore, this research was aiming to conduct an approach through analysis sentiment of public opinion about the veil and hijab to know how much accurate the sentiment analysis predict the positive, negative, or other sentiments with using Twitter data as the research object. The algorithm used in this study is Support Vector Machine (SVM) because of its fairly good classification model though it trained using small set of data. The SVM on this research was combined with Radial Base Function (RBF) kernel because of its numerical difficulties that are fewer than linear and polynomial kernel and also because this research doesn’t have a large feature.  The amount of data used is 3556 tweets data. Tweets data, which is numbered 1056, is classified manually for the learning process. The remaining 2500 data will be classified automatically with the classifier model that has been created. A total of 1056 tweets data that have been classified manually is separated into training and testing data with a ratio of 8: 2. The result of the sentiment analysis process using Support Vector Machine algorithm RBF kernel with C=1 and γ=1  has an accuracy score of 73.6% with precision to negative opinions are 62%, positive opinions are 83%, neutral opinions reach 53% and irrelevant opinions that talk about hijab and veil reach 98%. It shows that sentiment analysis can be used for predicting the negative, positive or other sentiments of a sentence based on a certain topic, in this case veil and hijab.
Comparative Evaluation of NDVI-Based Vegetation Classification Using Rule-Based Thresholding and Random Forest Models Nazhifah, Sri Azizah; Maulyanda; Putri, Andriani; Kiftiyani, Usfita
CYBERSPACE: Jurnal Pendidikan Teknologi Informasi Vol 9 No 2 (2025)
Publisher : Universitas Islam Negeri Ar-Raniry Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22373/agmq9j89

Abstract

This study aims to compare vegetation classification performance using NDVI derived from Sentinel-2A and Landsat 8 satellite imagery through two different approaches: rule-based classification and machine learning with the Random Forest algorithm. The rule-based approach applies a fixed NDVI threshold of 0.45 to distinguish vegetation and non-vegetation areas. In contrast, the Random Forest model was trained using 70% of the labeled data and tested on the remaining 30%, with NDVI values from both satellite sources as input features. The evaluation results show that the Random Forest model achieved perfect classification accuracy (100%). However, this may be due to using the same labeled dataset for both training and validation, which can lead to overfitting. On the other hand, the rule-based classification yielded an accuracy of 79.7%. This lower performance is likely caused by several factors, including the resolution differences between Sentinel-2 and Landsat 8 imagery, and the subjectivity involved in selecting the NDVI threshold value. The manual threshold setting may lead to bias and a higher number of misclassified pixels. Therefore, while rule-based methods are simple and interpretable, they are less robust. Machine learning approaches, such as Random Forest, offer more flexible and accurate classification when supported by properly separated training and validation datasets.
Co-Authors Lestari, Lusiana Maulyanda Nazhifah, Sri Azizah Putri, Andriani R Wahyudi, M Didik