Purpose The purpose of this paper is to analyze topics as alternative features for sentiment analysis in Indonesian tweets. Design/methodology/approach Given Indonesian tweets, the processes of sentiment analysis start by extracting features from the tweets. The features are words or topics. The authors use non-negative matrix factorization to extract the topics and apply a support vector machine to classify the tweets into its sentiment class. Findings The authors analyze the accuracy using the two-class and three-class sentiment analysis data sets. Both data sets are about sentiments of candidates for Indonesian presidential election. The experiments show that the standard word features give better accuracies than the topics features for the two-class sentiment analysis. Moreover, the topic features can slightly improve the accuracy of the standard word features. The topic features can also improve the accuracy of the standard word features for the three-class sentiment analysis. Originality/value The standard textual data representation for sentiment analysis using machine learning is bag of word and its extensions mainly created by natural language processing. This paper applies topics as novel features for the machine learning-based sentiment analysis in Indonesian tweets.

No abstract

Chaos based cryptography has becoming an interesting topic lately, as it utilizes chaotic systems properties for secure key concealment. Many chaotic functions are discovered, constructed, and used time over time for this purpose, which will be our main aim here. Two well known maps that has been known for exhibiting chaotic behaviors are the Gauss Map and the Circle Map, where the Circle Map has unlimited chaos potential, while the Gauss Map’s is much weaker and limited. In this paper, we investigate computationally using Python whether the Gauss Map can be improved by combining it with the Circle Map, allowing exploitation of greater chaotic behaviors. For this purpose, an improved version of the Gauss map is constructed, from which, we plot its bifurcation diagrams and Lyapunov exponents graphics, and show that it has a good potential to be a random number generator (RNG) using the NIST test, as these are the three main aspects of chaotic maps utilized in chaos based cryptography. The results obtained from this observation shows that composing the Circle Map into the Gauss Map, along with several manipulations, generates a significantly improved version of the Gauss Map, as it has a bifurcation diagram with much higher density, much higher Lyapunov exponents, and mostly better P-Values from the NIST tests, although it is still not fully suitable for a RNG. The manipulations done here, which aims to conserve the maps ranges to stay within the chaotic intervals and position the Circle Map to be the “variable” of the Gauss Map, allows the chaotic behaviors from the original maps to be bequeathed and strengthened in the new map.

Indonesia memiliki kekayaan berbagai jenis kain tradisional indah dan unik, salah satunya adalah kain tenun ikat. Tenun ikat memiliki pola-pola tertentu yang menghasilkan motif-motif khas untuk keperluan tradisional. Seiring dinamika perkembangan zaman dan selera fesyen yang berubah, maka perlu dilakukan pengembangan desain motif baru sesuai dengan tuntutan zaman. Penelitian dan penciptaan seni ini bertujuan melakukan diversifikasi produk baru dengan cara mengombinasikan teknik tenun ikat dan teknik batik dalam selembar kain. Metode yang digunakan adalah pengumpulan data, perancangan desain tenun ikat kombinasi batik, pengikatan dan pencelupan warna, penenunan, dan pembatikan. Tematik motif yang diangkat yaitu seni budaya Nusa Tenggara Timur. Produk baru paduan tenun dan batik ini disingkat nuntik (tenun dan batik). Kegiatan ini menghasilkan tujuh motif nuntik yaitu Motif

No abstract