Challenges in Applying Machine Learning Methods: Studying Political Interactions on Social Networks

2018 ◽  
pp. 136-141
Author(s):  
Chaya Liebeskind ◽  
Karine Nahon
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Learning Methods ◽  
Machine Learning Methods

scholarly journals Automatic Misinformation Detection About COVID-19 in Brazilian Portuguese WhatsApp Messages

2021 ◽  
Author(s):  
Antônio Diogo Forte Martins ◽  
José Maria Monteiro ◽  
Javam Machado
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Brazilian Portuguese ◽  
Primary Sources ◽  
Learning Methods ◽  
Data Set ◽  
Machine Learning Methods

During the coronavirus pandemic, the problem of misinformation arose once again, quite intensely, through social networks. In Brazil, one of the primary sources of misinformation is the messaging application WhatsApp. However, due to WhatsApp's private messaging nature, there still few methods of misinformation detection developed specifically for this platform. In this context, the automatic misinformation detection (MID) about COVID-19 in Brazilian Portuguese WhatsApp messages becomes a crucial challenge. In this work, we present the COVID-19.BR, a data set of WhatsApp messages about coronavirus in Brazilian Portuguese, collected from Brazilian public groups and manually labeled. Then, we are investigating different machine learning methods in order to build an efficient MID for WhatsApp messages. So far, our best result achieved an F1 score of 0.774 due to the predominance of short texts. However, when texts with less than 50 words are filtered, the F1 score rises to 0.85.

Predicting The Cricket Match Outcome Using Crowd Opinions On Social Networks: A Comparative Study Of Machine Learning Methods

2017 ◽  
Vol 30 (1) ◽  
pp. 63-76 ◽  
Author(s):  
Raza Ul Mustafa ◽  
M. Saqib Nawaz ◽  
M. Ikram Ullah Lali ◽  
Tehseen Zia ◽  
Waqar Mehmood
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Comparative Study ◽  
Learning Methods ◽  
Machine Learning Methods

scholarly journals Improving sentiment analysis for twitter data by handling negation rules in the Serbian language

2019 ◽  
Vol 16 (1) ◽  
pp. 289-311 ◽  
Author(s):  
Adela Ljajic ◽  
Ulfeta Marovac
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Sentiment Analysis ◽  
Learning Methods ◽  
Short Text ◽  
Machine Learning Methods ◽  
Relative Improvement ◽  
Twitter Data

The importance of determining sentiment for short text increases with the rise in the number of comments on social networks. The presence of negation in these texts affects their sentiment, because it has a greater range of action in proportion to the length of the text. In this paper, we examine how the treatment of negation impacts the sentiment of tweets in the Serbian language. The grammatical rules that influence the change of polarity are processed. We performed an analysis of the effect of the negation treatment on the overall process of sentiment analysis. A statistically significant relative improvement was obtained (up to 31.16% or up to 2.65%) when the negation was processed using our rules with the lexicon-based approach or machine learning methods. By applying machine learning methods, an accuracy of 68.84% was achieved on a set of positive, negative and neutral tweets, and an accuracy of as much as 91.13% when applied to the set of positive and negative tweets.

scholarly journals Using machine learning methods to determine Myers-Briggs Type Index (Mbti) types of people

2021 ◽  
Vol 1 (79) ◽  
pp. 32-39
Author(s):  
A. Myngzhassar ◽  
◽  
A. B. Kuldzhabekov ◽  
S. Daribayev ◽  
А. N. Temirbekov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Text Messages ◽  
Gradient Boosting ◽  
Learning Methods ◽  
Psychological Types ◽  
Machine Learning Methods ◽  
Extreme Gradient Boosting ◽  
Computer Linguistics ◽  
Myers Briggs

The article is based on the problems of machine learning in the field of computer linguistics, in particular, the identification of psychological types of people on the basis of text messages on social networks. The purpose of this article is to study the methods of machine learning Naive bayes and Extreme Gradient Boosting (XGBoost) to create a classifier for the Kazakh language, which determines the type of Myers-Briggs Type Index (MBTI) based on text samples of people’s posts on social networks. The course of research experiments in the use of machine learning methods and the results of the study are presented and the results obtained are compared.

Application of machine learning methods for automatic interpretation of open hole logging data

2020 ◽  
pp. 44-47
Author(s):  
M.A. Basyrov ◽  
◽  
A.V. Akinshin ◽  
I.R. Makhmutov ◽  
Yu.D. Kantemirov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Automatic Interpretation ◽  
Open Hole
Sign in / Sign up

Export Citation Format

Share Document