Book Title:

Deep Learning for Social Media Data Analytics

Editors:

• Prof. Dr. Tzung-Pei Hong, Kaohsiung University, Kaohsiung, Taiwan (Email: tphong@nuk.edu.tw)
• Dr. Leticia Serrano Estrada, University of Alicante, Alicante, Spain (Email: leticia.serrano@ua.es)
• Dr. Akrati Saxena, Eindhoven University of Technology, Eindhoven, Netherlands (Email: a.saxena@tue.nl)
• Dr. Anupam Biswas, National Institute of Technology Silchar, India (Email: anupam@cse.nits.ac.in)

About the Book:

Deep Learning for Social Media Data Analytics (smda21) is an edited book (multi-authored book) to be published at Studies in Big Data, Springer book series (Approval Awaited). Social networking platforms are overwhelmed by different contents like photos, videos or texts shared by billions of users. These huge volumes of data generated are mostly unstructured, which has enormous potential to influence business, politics, security, planning and other social aspects. Mostly, social media posts are in the form of texts, or text along with images or video. Natural language processing plays an important role in analyzing those texts and drawing useful conclusions, which are necessary for sentiment analysis or opinion mining. Users often upload photos without captions, which may be personal or related to other things. Thus, recognition of images or the generation of captions is quite helpful in drawing valuable information about the photo or posts containing photos. Nowadays, a major security related challenge in social media platforms is detection of fake news or rumors or misinformation. To tackle this issue multi-modal analysis of data involving text, image and video is often necessary/useful. Furthermore, deep learning is used immensely for analyzing text, images and videos. This type of information has a number of possible applications in very diverse fields. This book covers various applications of deep learning techniques in social media to solve different problems.

Topics include, but not limited to…

Deep learning techniques used in following topics of social media data analytics:

• Community Detection
• Link Prediction
• Sentiment Analysis
• Recommender System
• Opinion Mining
• Review Mining
• Hate Speech
• Rumor Detection
• Fake News Detection
• Social Media Security
• Image Recognition for Social Media Marketing
• Chatbots for Social Media Marketing
• Social Media Advertising
• Detection of Social Media Influencer
• Identification of Biased Information in Social Media
• Custom Topic Analysis for News Media
• Social Media Monitoring Agents
• Social Media for Effective Customer Service
• Mental Health Prediction/Analysis
• Anomalous user detection
• Spatiotemporal urban data analytics
• Social media data for urban planning

Tentative Schedule and Submission Link

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference. The following paper categories are welcome:

• All chapters must be original and not simultaneously submitted to another book, journal or conference.
• Chapters should not exceed similarity index of 10% excluding references.
• Chapter length 15-25 pages.
• Chapters should be formatted using Springer overleaf template https://www.overleaf.com/latex/templates/springer-book-chapter/hrdcrfynnzjn

Publication

All accepted book chapters will be published in Studies in Big Data, Springer book series (Approval Awaited). This series is indexed in SCOPUS, SCIMAGO, and zbMATH. All books published in the series are submitted for consideration in Web of Science.

No publication charge.

Comments