scholarly journals Perbandingan Metode Klasifikasi Random Forest dan SVM Pada Analisis Sentimen PSBB

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Muhammad Rivza Adrian ◽  
Muhammad Papuandivitama Putra ◽  
Muhammad Hilman Rafialdy ◽  
Nur Aini Rakhmawati
Keyword(s):  
Social Media ◽  
Random Forest ◽  
Local Governments ◽  
Large Scale ◽  
Training Data ◽  
Support Vector ◽  
Social Media Platform ◽  
Public Meetings ◽  
Svm Algorithm ◽  
Media Platform

COVID-19 in Indonesia, has made the local government not remain silent. Several local governments in Indonesia have enacted regulations to reduce the growth of COVID-19 victims by limiting public meetings with Large-Scale Social Restrictions or LSSR. However, the implementation of this LSSR has received many comments from social media users, especially from Twitter. This research was conducted with the aim of analyzing the sentiment of implementing the LSSR with media tweets on the Twitter social media platform. The data that were successfully extracted were 466 tweet data with training data and test data having a ratio of 7 to 3. Then the data was calculated into 2 different algorithms to be compared, the first algorithm used was the Support Vector Machine (SVM) algorithm and Random Forest with the aim get the most accurate sentiment analysis results.

scholarly journals Analisis Sentimen Pada Maskapai Penerbangan di Platform Twitter Menggunakan Algoritma Support Vector Machine (SVM)

Teknika ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 18-26
Author(s):  
Hendry Cipta Husada ◽  
Adi Suryaputra Paramita
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Support Vector Machine ◽  
Cross Validation ◽  
Support Vector ◽  
Learning Approach ◽  
Social Media Platform ◽  
Machine Learning Approach ◽  
Media Platform ◽  
Fold Cross Validation

Perkembangan teknologi saat ini telah memberikan kemudahan bagi banyak orang dalam mendapatkan dan menyebarkan informasi di berbagai social media platform. Twitter merupakan salah satu media yang kerap digunakan untuk menyampaikan opini sebagai bentuk reaksi seseorang atas suatu hal. Opini yang terdapat di Twitter dapat digunakan perusahaan maskapai penerbangan sebagai parameter kunci untuk mengetahui tingkat kepuasan publik sekaligus bahan evaluasi bagi perusahaan. Berdasarkan hal tersebut, diperlukan sebuah metode yang dapat secara otomatis melakukan klasifikasi opini ke dalam kategori positif, negatif, atau netral melalui proses analisis sentimen. Proses analisis sentimen dilakukan dengan proses data preprocessing, pembobotan kata menggunakan metode TF-IDF, penerapan algoritma, dan pembahasan atas hasil klasifikasi. Klasifikasi opini dilakukan dengan machine learning approach memanfaatkan algoritma multi-class Support Vector Machine (SVM). Data yang digunakan dalam penelitian ini adalah opini dalam bahasa Inggris dari para pengguna Twitter terhadap maskapai penerbangan. Berdasarkan pengujian yang telah dilakukan, hasil klasifikasi terbaik diperoleh menggunakan SVM kernel RBF pada nilai parameter 𝐶(complexity) = 10 dan 𝛾(gamma) = 1, dengan nilai accuracy sebesar 84,37% dan 80,41% ketika menggunakan 10-fold cross validation.

Witnessing in crisis contexts in the social media age: the case of the 2015 Tianjin blasts on Weibo

2019 ◽  
Vol 42 (5) ◽  
pp. 675-691 ◽  
Author(s):  
Xiaoping Wu ◽  
Martin Montgomery
Keyword(s):  
Social Media ◽  
Personal Experience ◽  
Large Scale ◽  
Chinese Characters ◽  
Industrial Accidents ◽  
Social Media Platform ◽  
Word And Image ◽  
Crisis Events ◽  
The Social ◽  
Media Platform

This study explores how the act of witnessing takes distinctive discursive shape in social media in the context of large-scale disasters or crisis events. Drawing upon a set of microblogs posted on China’s most widely used social media platform, Weibo, immediately after one of China’s most serious industrial accidents, this study shows how witnessing manifests itself through individual eyewitness accounts foregrounding personal experience but constrained within Weibo’s standard protocol of 140 Chinese characters. Often blending word and image, these accounts are examined using methodologies drawn from discourse analysis. On this basis, we argue that witnessing in social media in China not only demonstrates strong participatory, connective, and self-reflexive characteristics. It also opens up new possibilities for various patterns of meaning, which, when appropriated by other social media users, constitute a public testimony that can challenge official discourses of crisis in China.

scholarly journals FEATURE BASED ANALYSIS ON THE DUPLICATE FAKE ACCOUNT ON TWITTER USING INTELLIGENT MECHANISM

2021 ◽  
Vol 9 (1) ◽  
pp. 1315-1320
Author(s):  
Dr. Mohammed Ali Alhariri
Keyword(s):  
Social Media ◽  
Random Forest ◽  
Decision Tree ◽  
Machine Learning Techniques ◽  
Social Media Platform ◽  
Twitter Data ◽  
Learning Techniques ◽  
The Social ◽  
Feature Based ◽  
Media Platform

The duplicate fake accounts are detected in this work the data from the social media platform is accessed. The platform choose to use the analysis on social media platform is selected as twitter. The twitter data is accessed using Twitter API, with using some selected features that remain the most appropriate regarding the reason of duplicate fake account. The feature based analysis is compared using machine learning techniques, Random Forest, Decision Tree, and SVM. The performance is further analyzed based on accuracy SVM performed 93.3% accuracy, where decision tree performed as 89.0% and random forest performed as 85.5%. The better performance observed using feature-based analysis is of SVM.  

scholarly journals Crowdsourcing Cross-Disciplinary Collaboration in the Health Professions: A Novel Method and Tools for Replication (Preprint)

2020 ◽  
Author(s):  
Kimberly Acquaviva
Keyword(s):  
Social Media ◽  
Degree Completion ◽  
Large Scale ◽  
Health Professions ◽  
High Quality ◽  
Google Docs ◽  
Social Media Platform ◽  
The Social ◽  
Media Platform ◽  
Novel Method

BACKGROUND Authorship teams in the health professions are typically composed of scholars who are acquainted with one another before a manuscript is written. Even if a scholar has identified a diverse group of collaborators outside their usual network, writing an article with a large number of co-authors poses significant logistical challenges. OBJECTIVE This paper describes a novel method for crowdsourcing cross-disciplinary collaboration that facilitates the efficient development of diverse authorship teams and high-quality manuscripts. METHODS On September 11, 2020, I used the social media platform Twitter to invite people to collaborate on an article I had drafted. Anyone who wanted to collaborate was welcome, regardless of discipline, specialty, title, country of residence, or degree completion. During the twenty-five days that followed, I used Google Docs, Google Sheets, and Google Forms to manage all aspects of the collaboration. RESULTS The collaboration resulted in the completion of two manuscripts in a twenty-five day period. Forty collaborators met the ICMJE authorship criteria for the first article (“Documenting Social Media Engagement as Scholarship: A New Model for Assessing Academic Accomplishment for the Health Professions”) and thirty-five collaborators met the ICMJE authorship criteria for the second article (“The Benefits of Using Social Media as a Health Professional in Academia”). The authorship teams for both articles were notably diverse, with 17-18% of authors identifying as a person of color and/or under-represented minority, 37-38% identifying as LGBTQ+, 73-74% using she/her pronouns, and 20-23% identifying as a person with a disability. CONCLUSIONS Scholars in the health professions can use this paper in conjunction with the tools provided to replicate this process in carrying out their own large-scale manuscript collaborations.

Sosyal medyada Suriye’li sığınmacılara yönelik algı: bir sözlük değerlendirmesi

2017 ◽  
Vol 4 (2) ◽  
pp. 185-200 ◽  
Author(s):  
Servet Kardeş ◽  
Çağla Banko ◽  
Berrin Akman
Keyword(s):  
Qualitative Research ◽  
Social Media ◽  
Content Analysis ◽  
Syrian Refugees ◽  
Analysis Method ◽  
Social Media Platform ◽  
Content Analysis Method ◽  
Negative News ◽  
Media Platform ◽  
Made In

Bu araştırmada sığınmacılara yönelik paylaşımların yapıldığı sosyal medyada yer alan sözlüklerden birinde sığınmacılara yönelik algıya bakılmıştır. Yöntem olarak nitel desende olan bu çalışmada, bir sosyal medya sitesinde yer alan paylaşımlar içerik analizi yoluyla derinlemesine incelenip yorumlanmıştır. Araştırmanın sonucunda sosyal medya kullanıcılarının sığınmacıları büyük bir güvensizlik ortamı ve huzursuzluk yaratan bireyler olarak gördükleri saptanmış, sığınmacılarla yaşanan deneyimlerin ve medyadaki haberlerin bu düşüncelerin oluşmasında etkisinin olduğu belirlenmiştir. Bunun yanında sosyal medya kullanıcılarının devletin sığınmacılar konusunda yanlış politika izlediğini düşündükleri ve sığınmacılar için etkili bir planlama yapılmadığını ifade ettikleri görülmüştür. Çalışmanın sonuçları doğrultusunda medyada sığınmacılar hakkında çıkan haberlerde olumsuz ve şiddet temalı haberlerin azaltılması, Suriyeli sığınmacıların durumu, sahip oldukları haklar ve topluma yansımaları hakkında doğru ve bilgilendirici kamu spotları hazırlanması ayrıca sığınmacıların topluma entegre olma sürecinin her basamağında daha planlı ve etkili bir yol izlenmesi önerilebilir.ABSTRACT IN ENGLISHPerceptions about Syrian refugees on social media: an evaluation of a social media platformIn this research, posts which are about Syrian refugees were published in a social media platform, called as “sözlük” were investigated. The research is a qualitative research. The posts in this platform are analyzed with content analysis method. According to results of analyses, social media users see Syrian refugees as people who create an insecure and a restless environment. The experiences people had with them and news have an effect on this view. In addition, social media users think that government made inappropriate policies and ineffective plans about Syrian refugees. It is suggested negative news about Syrian refugees should be decreased and government should make safer policies. In addition, adaptation of refugees to society should be made in more planned and effective way.

Comparison of SVM, RF and SGD Methods for Determination of Programmer's Performance Classification Model in Social Media Activities

2020 ◽  
Vol 4 (2) ◽  
pp. 329-335
Author(s):  
Rusydi Umar ◽  
Imam Riadi ◽  
Purwono
Keyword(s):  
Social Media ◽  
Gradient Descent ◽  
Classification Model ◽  
Stochastic Gradient Descent ◽  
Support Vector ◽  
Svm Algorithm ◽  
Vector Machines ◽  
Performance Patterns ◽  
A Company

The failure of most startups in Indonesia is caused by team performance that is not solid and competent. Programmers are an integral profession in a startup team. The development of social media can be used as a strategic tool for recruiting the best programmer candidates in a company. This strategic tool is in the form of an automatic classification system of social media posting from prospective programmers. The classification results are expected to be able to predict the performance patterns of each candidate with a predicate of good or bad performance. The classification method with the best accuracy needs to be chosen in order to get an effective strategic tool so that a comparison of several methods is needed. This study compares classification methods including the Support Vector Machines (SVM) algorithm, Random Forest (RF) and Stochastic Gradient Descent (SGD). The classification results show the percentage of accuracy with k = 10 cross validation for the SVM algorithm reaches 81.3%, RF at 74.4%, and SGD at 80.1% so that the SVM method is chosen as a model of programmer performance classification on social media activities.

Value cocreation behavior of customers and companies on the Weibo social media platform

2020 ◽  
Vol 48 (3) ◽  
pp. 1-11
Author(s):  
Huiqin Zhang ◽  
Hai Lan ◽  
Xudong Chen
Keyword(s):  
Social Media ◽  
Service Quality ◽  
Customer Value ◽  
Two Dimensions ◽  
Customer Participation ◽  
Citizenship Behavior ◽  
Generation Process ◽  
Social Media Platform ◽  
Value Cocreation ◽  
Media Platform

The Weibo social media platform in China has an important role in the value-generation process between a company and a customer. We investigated the relationship between the service quality provided on a company's Weibo page and the two dimensions of customer value cocreation behavior, namely, participation and citizenship, as well as the moderating effect of collectivism on this relationship. Participants were 354 active users of Weibo. Our findings confirmed that the service quality provided on a company's Weibo page was critical to the generation of customer value cocreation behavior. Further, collectivism moderated this relationship, with higher levels of collectivism strengthening the Weibo page service quality and customer value cocreation behavior relationship. In addition, customer citizenship behavior was positively related to customer perceptions of brand image, whereas customer participation was not. Implications for companies in the Chinese context are discussed.

Earth-Science Outreach Using an Integrated Social Media Platform

GSA Today ◽  
2017 ◽  
Author(s):  
C.J. Spencer ◽  
K.L. Gunderson ◽  
C.W. Hoiland ◽  
W.K. Schleiffarth
Keyword(s):  
Social Media ◽  
Earth Science ◽  
Science Outreach ◽  
Social Media Platform ◽  
Media Platform
Sign in / Sign up

Export Citation Format

Share Document