Social Informatics

Name: Social Informatics | 7th International Conference, SocInfo 2015, Beijing, China, December 9-12, 2015, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

7th International Conference, SocInfo 2015, Beijing, China, December 9-12, 2015, Proceedings

Tie-Yan Liu Christie Napa Scollon Wenwu Zhu(Herausgeber*in)

Springer (Verlag)

Erschienen am 1. Dezember 2015

XII, 290 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-319-27433-1 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents
Culture, Imagined Audience, and Language Choices of Multilingual Chinese and Korean Students on Facebook
1 Introduction
2 Related Work
2.1 Collectivistic Culture and SNS Usage
2.2 Language Choice
2.3 The Imagined Audience
3 Methodology
3.1 Participants
3.2 Experiment Flow
Part 1. Online Scenario-Based Open-Ended Exercise.
Part 2. Two Surveys: Demographics and Facebook Posts.
Part 3. Exploratory Visualization of Language Usage on Facebook.
Part 4. Semi-Structured Interview.
3.3 Data Analysis
4 Results
4.1 Scenarios
4.2 Target Audience and Language Obligations
5 Discussion
5.1 Post Content and Cultural Considerations (RQ1)
Collectivistic Culture and L1.
Sharing Cultures in English.
5.2 Division of the Imagined Audience (RQ2)
Imagined Audience and Friendship Distribution.
Language Proficiency of the Poster and the Audience.
5.3 On the Other Side of the Barrier
6 Limitations
7 Conclusion
References
Analyzing Factors Impacting Revining on the Vine Social Network
1 Introduction
2 Dataset
3 User Behavior on Vine
3.1 Basic Analysis
3.2 Revining Behavior and Followers and Following
3.3 Revining and Temporal Behavior
3.4 Revining and Hash Tags
3.5 Revining and Followers
3.6 Revine Tree
4 Labeled Data Analysis
4.1 Revining and the Content/Emotion of Vines
4.2 Revining and Cyberbullying Vines
5 Conclusions
References
Who Stays Longer in Community QA Media? - User Behavior Analysis in cQA -
1 Introduction
2 Related Work
2.1 cQA Services Analysis
2.2 cQA User Motivation
2.3 Sequential Behavior Analysis and Phase Modeling
3 Macro Analysis of cQA User Behaviors
3.1 Dataset
3.2 Basic Statistics
4 Micro Analysis of cQA User Behaviors
4.1 User Phase Analysis
5 Discussion
6 Conclusion
References
Analyzing Labeled Cyberbullying Incidents on the Instagram Social Network
1 Introduction
2 Related Works
3 Data Collection
4 Cyberbullying Labeling
5 Analysis and Characterization of Ground Truth Data
5.1 Labeling and Negativity Analysis
5.2 Temporal and Graph Properties Analysis
5.3 Linguistic and Psychological Analysis
5.4 Image Content Analysis
6 Conclusions and Future Work
References
Uncovering Social Media Reaction Pattern to Protest Events: A Spatiotemporal Dynamics Perspective of Ferguson Unrest
1 Introduction
2 Related Work
3 Dataset
4 Data Preprocessing
4.1 Measurement of Reaction Types
4.2 Geo-tagged and Non-tagged Tweets
4.3 Media Outlets and Normal Users
5 Research Questions
5.1 What is the General Spatiotemporal Tweeting Patterns Across the US?
Spatial Distribution.
Temporal Trend.
5.2 What is the Spatiotemporal Tweeting Patterns in Local St. Louis?
Spatiotemporal Hotspots.
Text Analysis.
5.3 What are the Reaction Patterns in Different US Urban Areas in Space, Time and Content?
Twitter User Reaction in Space.
Text Analysis in Space and Time.
6 Conclusion
References
Detecting Opinions in a Temporally Evolving Conversation on Twitter
1 Introduction
2 Related Work
3 Temporal Opinion Detection Over an Evolving Conversation
3.1 Opinion Change Processes Over Time
3.2 Opinion Detection Models
4 Data Collection and Preprocessing
4.1 Data Collection
4.2 Data Cleaning and Preprocessing
5 Implementation Details
5.1 Feature Engineering
5.2 Implementation
6 Experimental Results
6.1 Temporal Opinion Detection Results
6.2 Significant Feature Detection and Emergence of Temporal Sub-Topics
7 Conclusion
References
Identifying Similar Opinions in News Comments Using a Community Detection Algorithm
1 Introduction
2 Background
2.1 Community Detection Algorithms
2.2 Louvain Community Detection
3 Methodology
3.1 Data Collection
3.2 Comparison with Manual Classification
4 Results
5 Discussion
6 Conclusions
References
Identifying Suggestions for Improvement of Product Features from Online Product Reviews
1 Introduction
2 Related Work
3 Feature Extraction
3.1 Delta TFIDF
3.2 Presence of an Aspect
3.3 Presence of Suggestive Phrases and Sentiment Score
3.4 Grammatical Dependencies
4 Experiments and Results
4.1 Data Collection and Annotation
4.2 Results
5 Conclusion
References
Crowdsourcing Safety Perceptions of People: Opportunities and Limitations
1 Introduction
2 Related Work
2.1 People Demographics and Safety Perception
2.2 Crowdsourcing Perceptions
3 Streetsmart
3.1 Selecting Features
3.2 Selecting Images
3.3 Online Crowdsourcing
4 Method
4.1 Data Collection
4.2 Hypotheses
4.3 Analysis
5 Results
5.1 Who We See
5.2 Who We Are
6 Discussion and Future Work
References
A Real-Time Crowd-Powered Testbed for Content Assessment of Potential Social Media Posts
1 Introduction
2 System Design
2.1 Topic Extraction
2.2 Specialist Identification
2.3 Representative Selection
2.4 Feedback Collection
2.5 Report Generation
3 Real-Time Crowdsourcing with Cassandra
4 System Prototyping
5 Performance Evaluation
5.1 Reliability
5.2 Benefit of Personality Diversification
5.3 Latency
6 Related Work
7 Conclusion
References
Adaptive Survey Design Using Structural Characteristics of the Social Network
1 Introduction
2 Related Work
3 Methodological Background
4 Results
5 Summary
References
Digital Stylometry: Linking Profiles Across Social Networks
1 Introduction
2 Related Work
3 Data Collection and Datasets
4 Models
4.1 Linguistic Models
4.2 Temporal Models
4.3 Combined Models
5 Evaluation Against Humans
6 Discussion and Conclusions
References
Autoregressive Model for Users' Retweeting Profiles
1 Introduction
2 Problem Statement
3 Related Work
4 Activity-Based User Profiling
5 Retweet Decision Model
5.1 Learning the Model (Training)
5.2 Testing the Model (Prediction)
5.3 Why Daywise Classifiers?
6 Features
6.1 Pairwise Influence
6.2 Content
6.3 Time
7 Parameters k and i
8 Experimental Setup
8.1 Dataset
8.2 Baseline Methods
9 Experimental Results and Discussion
10 Conclusion
References
Choosing the Right Home Location Definition Method for the Given Dataset
1 Introduction
2 Related Work
2.1 Estimating User Locations: Content Approach
2.2 Estimating User Locations: Social and Historical Tie Approach
3 Dataset
4 Radius of Gyration
5 Home Detection Methods
6 Discussion and Conclusions
References
Proposing Ties in a Dense Hypergraph of Academics
1 Introduction
2 Background and Related Work
3 Method
3.1 Link Mass
3.2 Link Similarity
4 Results
4.1 Recovering Link Mass
4.2 Proposals as Predictions
4.3 Discussion of Results
5 General Discussion
References
Photowalking the City: Comparing Hypotheses About Urban Photo Trails on Flickr
1 Introduction
2 Related Work
3 Methods and Material
3.1 Methodology
3.2 Datasets
4 Hypotheses
5 Experiments
5.1 Berlin
5.2 Los Angeles, London and New York
6 Discussion
7 Conclusion
References
Labor Saving and Labor Making of Valuein Online Congratulatory Messages
1 Introduction
2 Literature Review
3 Study Design: Exploring Value Understanding
4 Findings
4.1 Personal Birthday Posts
4.2 Sending and Receiving Birthday Posts with Dormant Ties
4.3 The Imagined Audience of Facebook Birthday Posts
5 Limitations
6 Discussion
6.1 Facebook News Feed as a Social Signifier of Facebook Birthday Posts
6.2 A Minuscule Sociotechnical System
6.3 The Virtual Social Secretary
6.4 Sociotechnical Design Implications and Anti-implications
References
Banzhaf Index for Influence Maximization
1 Introduction
2 Coalition Games and Banzhaf Index
3 Banzhaf Index Computation
4 Experiments
4.1 Experimental Setup
4.2 Comparison of Shapley Versus Banzhaf
4.3 Banzhaf vs Other Approaches
5 Conclusion
References
Modeling Social Media Content with Word Vectors for Recommendation
1 Introduction
2 Related Work
3 Method
3.1 Problem Formulation and Notation
3.2 Collaborative Filtering with Word Embedding-Based Topic Models
3.3 Parameter Estimation
4 Experiment
4.1 Group Recommendation in Meetup
4.2 Product Recommendation in Online Review Website
5 Conclusions and Future Work
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken