Suitability of Machine Learning Methods for Prediction of Popularity on Social Media in Comparison of Different Data Sets

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F21%3A50018796" target="_blank" >RIV/62690094:18450/21:50018796 - isvavai.cz</a>
Result on the web
<a href="https://uni.uhk.cz/hed/site/assets/files/1077/proceedings_2021_1-1.pdf" target="_blank" >https://uni.uhk.cz/hed/site/assets/files/1077/proceedings_2021_1-1.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.36689/uhk/hed/2021-01-025" target="_blank" >10.36689/uhk/hed/2021-01-025</a>

Result language
angličtina
Original language name
Suitability of Machine Learning Methods for Prediction of Popularity on Social Media in Comparison of Different Data Sets
Original language description
The growing popularity of various social media and the use of neural networks in recent years has brought predicting opportunities in various sectors. Social networks, in conjunction with neural networks, are often used in healthcare (prediction of whether a disease occurs or symptoms return) or business (what will be the profit or error rate of the products) and are playing an important economic and marketing change in the 21st century. The aim of the presented project is to contribute to a deeper understanding of which machine learning method to use for which data set in order to ensure the best possible prediction success across different industries. A total of 10 methods were used and the success of a total of 13 data files was tested with the help of specialized software for machine learning and the Python programming language. Of all the methods tested, the highest success rate on most datasets was with the Random Forrest method. The success rate ranged from 58.38% to 98.65%. Out of the total number of 13 datasets, the Random Forrest method was 5 times the best in accuracy.
Czech name
—
Czech description
—

Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)