Subtopic Deep Dive
Social Network Extraction
Research Guide
What is Social Network Extraction?
Social Network Extraction extracts relational structures like graphs and communities from textual and transactional data using graph mining, community detection, and link prediction algorithms.
Researchers apply these methods to social media texts for centrality measures and sentiment networks (Budi Susanto et al., 2012, 24 citations). Recent works focus on Twitter data for sentiment analysis and network inference (Ghulam Asrofi Buntoro, 2017, 133 citations; Auliya Rahman Isnain et al., 2021, 82 citations). Over 10 papers from 2009-2023 address extraction from online discussions.
Why It Matters
Social Network Extraction enables fraud detection in transaction graphs and e-commerce recommendations by revealing hidden user relationships. Budi Susanto et al. (2012) used centrality on Twitter networks for influence mapping in elections. Ghulam Asrofi Buntoro (2017) extracted sentiment networks from Jakarta governor discussions, aiding political analysis. Anatoliy Gruzd (2011) visualized virtual community structures via ICTA, supporting business intelligence from forums.
Key Research Challenges
Sarcasm in Sentiment Networks
Sarcasm detection disrupts accurate edge weighting in extracted networks. Debby Alita and Auliya Rahman Isnain (2020, 63 citations) used Random Forest to identify sarcasm in Indonesian tweets, but false positives remain high. Imbalanced classes exacerbate misclassification in social graphs.
Imbalanced Data Classification
Multi-class text data for link prediction suffers from class imbalance, skewing graph structures. Slamet Riyanto et al. (2023, 53 citations) compared metrics like F1-score across classifiers on imbalanced datasets. Precision-recall tradeoffs hinder reliable network extraction.
Scalable Text-to-Graph Inference
Converting large-scale social media texts to graphs requires efficient meta-search and TF-IDF weighting. Arif Ridho Lubis et al. (2021, 52 citations) forecasted words in time-series tweets using TF-IDF for dynamic networks. Real-time processing challenges persist for millions of posts.
Essential Papers
Applying the UTAUT Model to Explain the Students’ Acceptance of Mobile Learning System in Higher Education
Mohammed Amin Almaiah, Mahdi M. Alamri, Waleed Mugahed Al-Rahmi · 2019 · IEEE Access · 330 citations
Mobile learning applications have been growing in demand and popularity and have become a common phenomenon in modern educational systems, especially with the implementation of mobile learning proj...
Analisis Sentimen Calon Gubernur DKI Jakarta 2017 Di Twitter
Ghulam Asrofi Buntoro · 2017 · INTEGER Journal of Information Technology · 133 citations
Abstract. Jakarta Governor Election 2017 discussed in society or internet, especially Twitter. Everyone is free opine on Jakarta governor candidate 2017 so many opinions, not only positive or neutr...
Implementation of K-Nearest Neighbor (K-NN) Algorithm For Public Sentiment Analysis of Online Learning
Auliya Rahman Isnain, Jepi Supriyanto, Muhammad Pajar Kharisma · 2021 · IJCCS (Indonesian Journal of Computing and Cybernetics Systems) · 82 citations
This research was conducted to apply the KNN (K-Nearest Neighbor) algorithm in conducting sentiment analysis of Twitter users on issues related to government policies regarding Online Learning. Res...
Analisis Sentimen Terhadap Layanan Indihome Berdasarkan Twitter Dengan Metode Klasifikasi Support Vector Machine (SVM)
Rian Tineges, Agung Triayudi, Ira Diana Sholihati · 2020 · JURNAL MEDIA INFORMATIKA BUDIDARMA · 73 citations
In the year 2018, 18.9% of the population in Indonesia mentioned that the main reason for their use of the Internet is social media. One of the social media with an active user of 6.43 million user...
Analisis Sentimen Wacana Pemindahan Ibu Kota Indonesia Menggunakan Algoritma Support Vector Machine (SVM)
Primandani Arsi, Retno Waluyo · 2021 · Jurnal Teknologi Informasi dan Ilmu Komputer · 72 citations
<p class="Abstrak">Dewasa ini, media sosial berkembang pesat di internet, salah satu yang banyak digemari adalah Twitter. Berbagai topik ramai diperbincangkan di Twitter mulai dari ekonomi, p...
Analysis the Effect of Different Factors on the Development of Mobile Learning Applications at Different Stages of Usage
Mohammed Amin Almaiah, Mahdi M. Alamri, Waleed Mugahed Al-Rahmi · 2019 · IEEE Access · 64 citations
For the development effective and successful mobile learning applications, it is important to understand the users' requirements in different stages of usage. In this paper, we developed a new mode...
Pendeteksian Sarkasme pada Proses Analisis Sentimen Menggunakan Random Forest Classifier
Debby Alita, Auliya Rahman Isnain · 2020 · Jurnal Komputasi · 63 citations
Kalimat sindiran atau sarkasme masih sering digunakan oleh kalangan publik untuk mengungkapkan maksud isi hati dan pikiran baik itu yang disampaikan secara langsng maupun tidak langsung. Sarkasme d...
Reading Guide
Foundational Papers
Start with Budi Susanto et al. (2012) for Twitter centrality basics, then Anatoliy Gruzd (2011) for ICTA community text analysis, as they establish core extraction from social data.
Recent Advances
Study Ghulam Asrofi Buntoro (2017) for sentiment networks, Auliya Rahman Isnain et al. (2021) for KNN on online learning tweets, and Slamet Riyanto et al. (2023) for imbalance handling.
Core Methods
Core techniques: centrality and follower graphs (Susanto 2012), automated text-to-network (Gruzd 2011), Random Forest sarcasm filtering (Alita 2020), SVM sentiment (Tineges 2020), TF-IDF time-series (Lubis 2021).
How PapersFlow Helps You Research Social Network Extraction
Discover & Search
Research Agent uses searchPapers and exaSearch to find Twitter network papers like 'Penerapan Social Network Analysis dalam Penentuan Centrality Studi Kasus Social Network Twitter' (Budi Susanto et al., 2012), then citationGraph reveals 24 citing works on centrality, and findSimilarPapers uncovers sentiment extraction analogs.
Analyze & Verify
Analysis Agent runs readPaperContent on Buntoro (2017) to extract Twitter sentiment methods, verifies graph claims with verifyResponse (CoVe) against Gruzd (2011), and uses runPythonAnalysis with pandas/NetworkX to recompute centrality scores, graded by GRADE for statistical rigor.
Synthesize & Write
Synthesis Agent detects gaps in sarcasm handling across Alita (2020) and Isnain (2021), flags contradictions in imbalance metrics (Riyanto 2023), then Writing Agent applies latexEditText for graph descriptions, latexSyncCitations for 10+ papers, and latexCompile for a review manuscript with exportMermaid community diagrams.
Use Cases
"Reproduce centrality measures from Budi Susanto 2012 Twitter network paper using Python"
Research Agent → searchPapers → Analysis Agent → readPaperContent + runPythonAnalysis (NetworkX centrality on tweet follower data) → matplotlib graph output with verified metrics.
"Write LaTeX review of sentiment-based social networks from Indonesian Twitter papers"
Synthesis Agent → gap detection on Buntoro 2017 + Isnain 2021 → Writing Agent → latexEditText + latexSyncCitations + latexCompile → PDF with embedded network diagrams.
"Find GitHub repos implementing ICTA-like community analyzers from Gruzd 2011"
Research Agent → findSimilarPapers on Gruzd 2011 → Code Discovery → paperExtractUrls → paperFindGithubRepo → githubRepoInspect → NetworkX code snippets for virtual community extraction.
Automated Workflows
Deep Research workflow scans 50+ papers via searchPapers on 'Twitter social network extraction', structures reports with centrality and sentiment sections using DeepScan's 7-step verification. Theorizer generates hypotheses on sarcasm effects in graphs from Alita (2020) and Riyanto (2023), chaining CoVe for robust predictions.
Frequently Asked Questions
What is Social Network Extraction?
Social Network Extraction derives graphs from text using community detection and centrality algorithms, as in Budi Susanto et al. (2012) on Twitter followers.
What methods are used?
Methods include centrality measures (Susanto 2012), ICTA text analysis (Gruzd 2011), Random Forest for sarcasm (Alita 2020), and TF-IDF forecasting (Lubis 2021).
What are key papers?
Foundational: Susanto et al. (2012, 24 citations), Gruzd (2011, 9 citations). Recent: Buntoro (2017, 133 citations), Isnain et al. (2021, 82 citations).
What are open problems?
Challenges include sarcasm detection (Alita 2020), imbalanced classification (Riyanto 2023), and scalable inference from dynamic texts (Lubis 2021).
Research Information Retrieval and Data Mining with AI
PapersFlow provides specialized AI tools for Computer Science researchers. Here are the most relevant for this topic:
AI Literature Review
Automate paper discovery and synthesis across 474M+ papers
Code & Data Discovery
Find datasets, code repositories, and computational tools
Deep Research Reports
Multi-source evidence synthesis with counter-evidence
AI Academic Writing
Write research papers with AI assistance and LaTeX support
See how researchers in Computer Science & AI use PapersFlow
Field-specific workflows, example queries, and use cases.
Start Researching Social Network Extraction with AI
Search 474M+ papers, run AI-powered literature reviews, and write with integrated citations — all in one workspace.
See how PapersFlow works for Computer Science researchers