scholarly journals Analisis Graph Clustering Terhadap User Behavior Di Official Account Facebook Universitas Bina Darma Palembang

2020 ◽  
Vol 1 (2) ◽  
pp. 63-76
Author(s):  
Ayu Gahardina ◽  
Ilman Zuhri Yadi
Keyword(s):  
Social Media ◽  
User Behavior ◽  
Graph Clustering ◽  
Network Visualization ◽  
Financial Fraud ◽  
Graph Visualization ◽  
Targeted Attacks ◽  
Data Clusters ◽  
Using Data ◽  
The Times

At a time when the times are increasing, it cannot be denied that almost some people use social media as a means of communication. Not only is it a means of communication, even social media is a place to show their habits. Without realizing it, the more information that is spread on social media regarding self-information, it will make information that can benefit others. User Behavior Analytics as defined by Gartner is a cybersecurity process of detection of insider threats, targeted attacks and financial fraud. The UBA solution looks at patterns of human behaviour and then applies algorithms and statistical analysis to detect meaningful anomalies of those patterns. Gephi is an open-source network visualization platform that can be used to analyze various cases using graph visualization. One of these analyzes can be done by using data that has been scraped from social media, Facebook, social media, Bina Darma University to get data visualization of the cases being tested. From these results, the graph clustering process is carried out in Gephi to obtain data clusters. The results will then be analyzed and identified so that they can become material for information about social media user behaviour.

scholarly journals Analyzing temporal patterns of topic diversity using graph clustering

2020 ◽  
Author(s):  
Takako Hashimoto ◽  
David Lawrence Shepard ◽  
Tetsuji Kuboyama ◽  
Kilho Shin ◽  
Ryota Kobayashi ◽  
...  
Keyword(s):  
Social Media ◽  
Data Processing ◽  
Temporal Patterns ◽  
Graph Clustering ◽  
Disaster Mitigation ◽  
Great Earthquake ◽  
Using Data ◽  
Text Content ◽  
Do So

Abstract During a disaster, social media can be both a source of help and of danger: Social media has a potential to diffuse rumors, and officials involved in disaster mitigation must react quickly to the spread of rumor on social media. In this paper, we investigate how topic diversity (i.e., homogeneity of opinions in a topic) depends on the truthfulness of a topic (whether it is a rumor or a non-rumor) and how the topic diversity changes in time after a disaster. To do so, we develop a method for quantifying the topic diversity of the tweet data based on text content. The proposed method is based on clustering a tweet graph using Data polishing that automatically determines the number of subtopics. We perform a case study of tweets posted after the East Japan Great Earthquake on March 11, 2011. We find that rumor topics exhibit more homogeneity of opinions in a topic during diffusion than non-rumor topics. Furthermore, we evaluate the performance of our method and demonstrate its improvement on the runtime for data processing over existing methods.

scholarly journals Social Media Listening pada Instagram untuk Kasus Kebakaran Hutan di Indonesia Menggunakan Graph Clustering

2019 ◽  
Vol 6 (2) ◽  
pp. 149
Author(s):  
Rina Trisminingsih ◽  
Riski Adi Kurniawan
Keyword(s):  
Social Media ◽  
Social Network ◽  
Forest Fire ◽  
Clustering Analysis ◽  
Graph Clustering ◽  
Graph Visualization ◽  
Web Based ◽  
Analysis Process ◽  
The Social ◽  
Data Source

<p><em>Social media listening </em>merupakan salah satu metode untuk melakukan analisis media sosial berbasis graf untuk mengidentifikasi dan menilai suatu isu yang sedang banyak dibicarakan di media sosial. Penelitian ini melakukan <em>social media listening </em>terkait isu kebakaran hutan dari data Instagram untuk melihat lebih dalam topik pembicaraan warganet terkait isu kebakaran hutan serta mengidentifikasi isu-isu terkait lainnya yang muncul. Pada penelitian ini dilakukan g<em>raph clustering </em>pada data Instagram dengan perangkat Gephi sehingga menghasilkan suatu graf dengan jumlah <em>node </em>sebanyak 36 dengan persentase 0.68% dari jumlah <em>node</em> awal sebanyak 5280 dan jumlah <em>edge </em>sebanyak 553 dengan persentase 0.92% dari jumlah <em>edge </em>awal sebanyak 64969. Proses <em>labeling</em> hasil <em>graph</em> <em>clustering</em> menghasilkan lima kelompok <em>hashtag</em> yaitu kategori isu lain yang muncul terkait kasus kebakaran hutan, kategori isu yang tidak berhubungan dengan kasus kebakaran hutan, kategori <em>hashtag</em> terkait lokasi kasus kebakaran hutan, kategori <em>hashtag</em> tentang slogan yang muncul pada kasus kebakaran hutan, dan kategori <em>hashtag</em> yang menggambarkan isu kebakaran hutan di Indonesia. Representasi graf dan hasil labelisasi kemudian divisualisasikan dalam aplikasi berbasis web untuk memudahkan identifikasi dan penilaian topik <em>(hashtag) </em>terkait isu kebakaran hutan di Indonesia.</p><p> </p><p> <strong>Abstract</strong></p><p><em>Social media listening is a method for conducting social network analysis by identifying and collecting information that can be used as the data source in certain cases. Using social media listening, we can summarize and get pattern from certain cases, for example in this study using  forest fire case in Indonesia. This research used hashtags from Instagram as the data source and conducted an analysis to understand the social interaction inside of forest fire case. The analysis aimed to obtain information summary using graph clustering on Gephi. Graph visualization was done using two-stage processess, which are modularity and filtering. This research resulted in 36 nodes with the percentage of 0.68% from 5280 initial nodes and 553 edges with the percentage of 0.92% from 64969 initial edges. The analysis process showed five clusters that represented the information summary from the graph clustering analysis result. The formed clusters were then analyzed and visualised on a web-based application to identifiy towards the node that represented another issues which appeared in the forest fire cases in Indonesia.</em></p>

FACEBOOK SEBAGAI MEDIA BARU TAFSIR AL-QUR’AN DI INDONESIA

2018 ◽  
Vol 2 (2) ◽  
pp. 69-80
Author(s):  
Wildan Imaduddin Muhammad
Keyword(s):  
Social Media ◽  
Methodological Problem ◽  
The Self ◽  
Internet Technology ◽  
Basic Character ◽  
Hermeneutic Approach ◽  
The Times ◽  
Qur'anic Interpretation

This article analyzes the product of Salman Harun's Qur'anic  interpretation with  Facebook  as the medium. As one of the senior professors who pursue the field of interpretation, he has managed to follow the times by utilizing internet technology. There are two focus areas in the study; the first aspect of the sense of Indonesian tafsir attached to the self of Salman Harun, the two aspects of the novelty of discourse that became the basic character of social media. Both aspects are interesting to be studied with a hermeneutic approach. Given that  the  methodological problem that often arises from the hermeneutic approach is the context of the interpreter that is difficult to trace accurately, then this article finds its relevance to the case of Salman Harun's interpretation which uses the facebook media as the actualization of its interpretation product.

Predictability of User Behavior in Social Media: Bottom-Up v Top-Down Modeling

2013 ◽  
Author(s):  
David Darmon ◽  
Jared Sylvester ◽  
Michelle Girvan ◽  
William M. Rand
Keyword(s):  
Social Media ◽  
User Behavior ◽  
Top Down ◽  
Bottom Up

Does Social Media Engagement Translate to Civic Engagement Offline?

2021 ◽  
pp. 089976402199944
Author(s):  
Jaclyn Piatak ◽  
Ian Mikkelsen
Keyword(s):  
Social Media ◽  
Civic Engagement ◽  
Presidential Election ◽  
Civic Participation ◽  
Political Engagement ◽  
Political Campaigns ◽  
The Internet ◽  
Online Engagement ◽  
Informal Volunteering ◽  
Using Data

People increasingly engage in politics on social media, but does online engagement translate to offline engagement? Research is mixed with some suggesting how one uses the internet maters. We examine how political engagement on social media corresponds to offline engagement. Using data following the 2016 U.S. Presidential Election, we find the more politically engaged people are on social media, the more likely they are to engage offline across measures of engagement—formal and informal volunteering, attending local meetings, donating to and working for political campaigns, and voting. Findings offer important nuances across types of civic engagement and generations. Although online engagement corresponds to greater engagement offline in the community and may help narrow generational gaps, this should not be the only means to promote civic participation to ensure all have a voice and an opportunity to help, mobilize, and engage.

Improving sentiment scoring mechanism: a case study on airline services

2018 ◽  
Vol 118 (8) ◽  
pp. 1578-1596 ◽  
Author(s):  
Wandeep Kaur ◽  
Vimala Balakrishnan
Keyword(s):  
Social Media ◽  
Content Type ◽  
Exclamation Mark ◽  
Semantic Orientation ◽  
Social Media Text ◽  
Major Airlines ◽  
Using Data ◽  
Sentiment Score ◽  
Repeated Letter ◽  
Facebook Pages

Purpose The purpose of this paper is to investigate the effect of including letter repetition commonly found within social media text and its impact in determining the sentiment scores for two major airlines in Malaysia. Design/methodology/approach A Sentiment Intensity Calculator (SentI-Cal) was developed by assigning individual weights to each letter repetition, and tested it using data collected from official Facebook pages of the airlines. Findings Evaluation metrics indicate that SentI-Cal outperforms the baseline tool Semantic Orientation Calculator (SO-CAL), with an accuracy of 90.7 percent compared to 58.33 percent for SO-CAL. Practical implications A more accurate sentiment score allows airline services to easily obtain a better understanding of the sentiments of their customers, hence providing opportunities in improving their airline services. Originality/value Proposed mechanism calculates sentiment intensity of social media text by assigning individual weightage to each repeated letter and exclamation mark thus producing a more accurate sentiment score.

An Experimental Study of Spammer Detection on Chinese Microblogs

2020 ◽  
Vol 30 (11n12) ◽  
pp. 1759-1777
Author(s):  
Jialing Liang ◽  
Peiquan Jin ◽  
Lin Mu ◽  
Jie Zhao
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
User Behavior ◽  
Real Data ◽  
User Profile ◽  
Data Set ◽  
Sina Weibo ◽  
Factors Affecting ◽  
The Government ◽  
Hot Event

With the development of Web 2.0, social media such as Twitter and Sina Weibo have become an essential platform for disseminating hot events. Simultaneously, due to the free policy of microblogging services, users can post user-generated content freely on microblogging platforms. Accordingly, more and more hot events on microblogging platforms have been labeled as spammers. Spammers will not only hurt the healthy development of social media but also introduce many economic and social problems. Therefore, the government and enterprises must distinguish whether a hot event on microblogging platforms is a spammer or is a naturally-developing event. In this paper, we focus on the hot event list on Sina Weibo and collect the relevant microblogs of each hot event to study the detecting methods of spammers. Notably, we develop an integral feature set consisting of user profile, user behavior, and user relationships to reflect various factors affecting the detection of spammers. Then, we employ typical machine learning methods to conduct extensive experiments on detecting spammers. We use a real data set crawled from the most prominent Chinese microblogging platform, Sina Weibo, and evaluate the performance of 10 machine learning models with five sampling methods. The results in terms of various metrics show that the Random Forest model and the over-sampling method achieve the best accuracy in detecting spammers and non-spammers.

Marketing Public Relations Melalui Instagram Screamous

2020 ◽  
Vol 2 (4) ◽  
pp. 361-380
Author(s):  
Nathasya Wiguna Wiguna ◽  
Nathasya Wiguna Dang Eif Dono Darsono
Keyword(s):  
Social Media ◽  
Data Collection ◽  
Public Relations ◽  
Descriptive Analysis ◽  
Active Role ◽  
Online Media ◽  
Good Citizen ◽  
Special Events ◽  
Pull Strategy ◽  
The Times

ABSTRAK Nathasya Wiguna, Marketing Public Relations Melalui Instagram Screamous (Analisis Deskriptif pada Instagram @Screamous_55) Media sosial Instagram media dan seiring dengan berkembangnya zaman, Instagram menjadi salah satu media sosial yang cukup diminati untuk kepentingan komunikasi pemasaran, dengan ciri khasnya mengedepankan pesan visual dan audio visual dengan interaktivitas yang tinggi. Marketing Public Relations Instagram Screamous menjadikan instagram sebagai media atau saluran dalam berbisnis salah satunya di bidang fashion. Screamous dalam hal ini memiliki peran aktif dalam mengelola dan menginformasikan sebuah produk melalui media online.  Penelitian ini bertujuan untuk meraih penyampaian informasi, mengenalkan brand dan produk serta menerapkan bangga akan produk lokal dengan menciptakan opini yang menguntungkan dan berhasilnya pemasaran. Selain itu bertujuan untuk mengetahui pull strategi dalam menarik minat konsumen terhadap konsumen, dengan push strategi yang mendorong berhasilnya pemasaran dan menggunakan pass strategi dalam memberikan opini yang menguntungkan. Metode yang digunakan dalam penelitian ini adalah Kualitatif dengan pendekatan analisis desktiptif dan menerapkan paradigma konstruktivisme, kemudian teknik yang di gunakan pada penelitian ini adalah teknik pengumpulan data, observasi partisipatori pasif, wawancara mendalam dan studi dokumen. Penelitian ini dilakukan melalui langkah-langkah : menentukan lokasi penelitian, menentukan metode penelitian, menentukan pemilihan informan, menentukan sumber dan jenis data, menentukan teknik pengumpulan data serta mengolah dan menganalisis data. Hasil penelitian ini menunjukan bahwa dalam mengenalkan dan mempertahankan brand lokal, dalam menunjang berhasilnya pemasaran. Screamous mengajak kepada para konsumen menyatukan suatu pemahaman bahwa sebagai warga negara yang baik, harus bangga akan produk lokal atau produk  dalam negeri. Marketing Public Relations Melalui Instagram Screamous dalam mempromosikan suatu produk terdiri dari Pull Strategy dalam menarik minat melalui campaign di produk atau barang Screamous dan melakukan kegiatan promosi melalui media online, dan media sosial. Push Strategy Screamous melalui spesial event, seperti kickfest, expo dalam mendorong berhasilnya pemasaran. Pass Strategy Screamous dalam menciptakan opini yang menguntungkan melalui kegiatan sponsorship seperti acara seminar, edukasi, acara musik dalam menjalin kerjasama dan membantu generasi bangsa dalam berkarya. Kata Kunci :Pemasaran, Instagram, dan Screamous ABSTRACT Nathasya Wiguna, Marketing Public Relations Through Instagram Screamous (Deskriptive analysis on Instagram @Screamous_55) Instagram media social media and along with the times, Instagram has become one of the social media that is in great demand for marketing communication purposes, with its trademark promoting visual and audio visual messages with high interactivity. Marketing Public Relations Instagram Screamous makes Instagram as a media or channel in doing business, one of them is in the fashion sector. Screamous in this case has an active role in managing and informing a product through online media. This study aims to achieve information delivery, introduce brands and products and apply pride in local products by creating favorable opinions and marketing success. In addition, it aims to find out the pull strategies in attracting consumer interest to consumers, with push strategies that encourage successful marketing and use pass strategies in providing favorable opinions. The method used in this study is qualitative with descriptive analysis approach and applying the constructivism paradigm, then the techniques used in this study are data collection techniques, passive participatory observation, in-depth interviews and document studies. This research was carried out through steps: determining the location of the study, determining the research method, determining the selection of informants, determining the source and type of data, determining the data collection techniques and processing and analyzing data. The results of this study indicate that in introducing and maintaining a local brand, in supporting the success of marketing. Screamous invites consumers to unite an understanding that as a good citizen, they must be proud of local products or domestic products. Marketing Public Relations Through Instagram Screamous in promoting a product consists of Pull Strategy in attracting interest through campaigns on Screamous products or goods and conducting promotional activities through online media, and social media. Push Strategy Screamous through special events, such as kickfest, expo in encouraging marketing success. Strategy Screamous Pass in creating favorable opinions through sponsorship activities such as seminars, education, music events in collaborating and helping the nation's generation in work.   Keywords: Marketing, Instagram, and Screamous  

Sign in / Sign up

Export Citation Format

Share Document