No abstract

This paper describes personality classification experiment by applying k-means clustering machine learning algorithms. Several previous studies have been attempted to predict personality types of human beings automatically by using various machine learning algorithms. However, only few of them have obtained good accuracy results. To classify a person into personality types, we used Jungian Type Inventory. Our method consists of three parts: data collection, data preparation, and hyper-parameter tuning. Our testing results showed that the k-means model has 107 inertia value, which is a good number for an unsupervised learning model as an interim result. With the result, we divided the data into 16 clusters, which can be considered as personality types. We continue this research with analysis of large data to be collected in the future.

Hackathons are special activities, which normally last about 1-3 days with teams to present their innovative solutions to the given problems in the IT domain. In this paper, we report the Paragon IT hackathon developing a web application using Facebook API and our analysis of surveys from the hackathon participants. We list and analyze the statistics of participants as their gender, age, level of satisfaction, and the willingness of attending another hackathon. Then, we mention participants’ primary motivation to participate, things they learned from the hackathon, and the main challenges. Based on that, we make some recommendations how to improve this hackathon even better. The results can be extrapolated into other hackathons, especially in Asian countries.

Kazakh is an agglutinative language which has complex structure. In this work Apache Spark was used to specify the popularity of Kazakh words in 3 popular kazakh compositions. The main goal was to find the optimal number of data segments for a specific number of cores in order to find the best computational speed. To do so, the data was divided into several segments and ran on a cluster with a different number of cores each time. Results show that the amount of data segments directly affects the computing speed.

This article describes image based personality type prediction. With the help of the Instagram API, photos of respondents who previously passed the MBTI test were collected. As a result, 60 percent of accuracy was achieved. This work represents one of the solutions to determine what personality type a person belongs to without passing any tests, but simply uploading an image.