No abstract

No abstract

The amount of production data generated by social media opportunities that can be exploited by various parties, both government and private sectors to produce the information. Social media data can be used to know the behavior and public perception of the phenomenon or a particular event. To obtain and analyze social media data needed depth knowledge of Internet technology, social media, databases, data structures, information theory, data mining, machine learning, until the data and information visualization techniques. In this research, social media analysis on a particular topic and the development of prototype devices software used as a tool of social media data retrieval or retrieval of data applications. Social Media Analytics (SMA) aims to make the process of analysis and synthesis of social media data to produce information can be used by those in need. SMA process is done in three stages, namely: Capture, Understand and Present. This research is exploratorily focused on understanding the technology that became the basis of social media using various techniques exist and is already used in the study of social media analytic previously..

Many parameters affect the timeliness of student graduation, starting from the student's interest in certain majors, the type of class chosen, to the grades for each semester obtained. This is a determining factor in how students can graduate on time or not at the end of their education. So a model is needed to predict student graduation rates on time, using alumni data whose data is obtained from several universities in Palembang City. The model used is a Naïve Bayes algorithm which serves as a model for classification. The dataset used is alumni data that has been collected from several universities, while the attributes used are the Department, College, Class Type, Temporary IP Value from semester 1 to 4, graduation year, and college generation. Then from the attributes and models used, the researcher used the Python 3 programming language and the Jupyter Notebook tools to process the prepared dataset. Furthermore, the distribution of the dataset is divided by 70% for training data and 30% for testing data. To test the algorithmic process used by researchers using K-Fold Validation. The results of this study are the accuracy of the prediction model carried out, where the accuracy results obtained from the Python 3 programming language and the Naïve Bayes algorithm are 0.8103.

Geospatial data on the media social like Twitter can be used to determine the spatial information (location), which is the location of the source of the emergence of public perception of an issue in social media AbstrakData geospasial pada media sosial Twitter dapat dimanfaatkan untuk mengetahui informasi spasial (lokasi) yang merupakan lokasi sumber munculnya persepsi publik terhadap sebuah isu di media sosial. Besarnya produksi data geospasial yang dihasilkan oleh Twitter memberikan peluang besar untuk dapat dimanfaatkan oleh berbagai pihak sehingga menghasilkan informasi yang lebih bernilai melalui proses Twitter Data Analytics. Proses pemanfaatan data geospasial Twitter dimulai dengan melakukan proses ekstraksi terhadap informasi spatial berupa titik koordinat pengguna Twitter. Titik koordinat pengguna Twitter didapatkan dari sharing location yang dilakukan oleh pengguna Twitter. Untuk mengekstrak dan menganalisis data geospasial pada Twitter dibutuhkan pengetahuan dan kerangka kerja tentang social media analytics (SMA). Pada penelitian ini dilakukan ekstraksi dan analisis data geospasial Twitter terhadap suatu isu publik yang sedang berkembang dan mengembangakan prototipe perangkat lunak yang digunakan untuk mendapatkan data geospasial yang ada pada Twitter. Proses ekstraksi dan analisis dilakukan melalui empat tahapan yaitu: proses penarikan data (crawling), penyimpanan (storing), analisis (analyzing), dan visualisasi (vizualizing). Penelitian ini bersifat exploratory yang terfokus pada pengembangan teknik ekstrasi dan analisis terhadap data geospasial twitter.