ACM Transactions on Asian and Low-resource Language Information Processing

Special Issue on Challenges and Trending Solutions for Cognitive Analytics of Social Multi-modal Text in Asian Indigenous Languages

Guest Editors:

• Deepak Kumar Jain, Chongqing University of Posts & Telecommunications, China, dkj@ieee.org
• Thierry Boumans, University La Rochelle, France, tbouwman@univ-lr.fr
• Stefano Berretti, University of Florence, Italy, stefano.berretti@unifi.it

With the proliferation of social networks (Twitter, Tumblr, Google+, Facebook, Instagram, Snapchat, YouTube, etc.), users can post and share all kinds of multi-modal text in the social setting using Internet without much knowledge about the Web’s client-server architecture and network topology. Multi-modal text defines a combination of two or more semiotic systems, which studies the visual, linguistic, audio, gestural and spatial signs and symbols to create meaning. Interestingly, the social multi-modal data is estimated to be 90% unstructured further making it crucial to tap and analyze information using contemporary tools. This proffers novel opportunities and challenges to leverage this high-diversity multi-modal data. At the same time, the resource-poor Indigenous languages are very challenging when dealing with NLP tasks and applications because of multiple reasons

Especially, the Asian social networking market dominates the world landscape with the highest consumer penetration rate. Businesses and investors often look for winning strategies to attract consumers to increase revenues from sales, advertisements, and other services offered on social media platforms. Current studies on social media are based on English language sociolinguistic cues and studies in local and regional Asian indigenous languages needs further exploration. Recently, cognitive analytics as a technology-based solution has attracted a lot of attention by both researchers and practitioners. It is a novel approach to information discovery and decision making, which uses multiple intelligent technologies such as machine learning, deep learning, artificial intelligence, natural language processing and image recognition among others to understand data then generate insights. It is touted as the key to unlock big data in the social setting for practical data-driven decision making.

The special issue aims to stimulate discussion on the design, use and evaluation of self-correcting and human cognition for continuous learning as the key knowledge discovery drivers within the socially connected ecosystem especially for NLP tasks pertaining to Asian indigenous languages. We encourage submission of articles describing cognitive models for resource-poor social media analytics to leverage deeper insights from the vast amount of generated data delivering a near real-time intelligence. Concurrently, we also welcome theoretical work and review articles on cognitive social media analytics framework.

Topics

The list of topic includes but not limited to:

• Cognitive modelling for social media analytics using Asian Indigenous Languages
• Trend and network analysis in Asian networks
• Sentiment analysis in Asian Indigenous Languages
• Monitoring emotion/rumour/bully in social data multi-modalities of Asian Indigenous Languages
• Speech recognition and language generation using Asian Indigenous Languages
• Cognitive robots, chat-bots and agents using Asian Indigenous Languages
• Multi-modal interfaces in cognitive social media systems using Asian Indigenous Languages
• Conversational AI for Asian Indigenous Languages

Important Dates

• Submission Open: 20^th Feb 2023
• Submission deadline: 30^th Aug 2023
• First-round review decisions: 20^th Oct 2023
• Deadline for revision submissions: 30^th Nov 2023
• Notification of final decisions: 30^th Dec 2023
• Tentative publication: As per journal policy

Submission Information

Please refer https://dl.acm.org/journal/tallip/author-guidelines and select “Automated Knowledge Extraction and Natural Language Processing for Lexicography of Low Resource Languages” in the TALLIP submission site, https://mc.manuscriptcentral.com/tallip

For questions and further information, please contact Dr. Deepak (dkj@ieee.org)