People share their thoughts, emotions, views, and knowledge on social media platforms. They are often comfortable in their native languages and as a result there is now a significant volume of online content being generated in various languages. Microblogging and online social media platforms such as Twitter, Facebook, and LinkedIn are platforms that allow people to share their feelings, opinions, thoughts, and emotions. A good amount of information flow in social media is in code-mixed languages. Online users’ opinion and emotions can find applications in multiple fields. However, current NLP systems and algorithmic frameworks focus more on analysing content in high-resource languages such as English despite the fact that there is now a large volume of text in various online platforms that are in low resource languages. Therefore, there is a need to develop computational approaches and algorithmic frameworks for automated processing of texts in low resource languages in the context of emotions, feelings and mental health. This special issue is an attempt to attract attention of researchers towards this end and on expanding the knowledge base in this context. The special issue welcomes contributions reporting advances in NLP approaches and methods inspired by AI towards analysing code-mixed or low-resource languages’ content on online social media in the context of emotions, feelings, and mental health. Submissions reporting newly curated and annotated datasets in low resource languages are also welcome.

Topics
The indicative topics of interest are as follows:
• Abusive content detection
• Cyber stalking
• Cyberbullying detection
• Datasets for emotion and sentiment
• Dialogue systems
• Disfluency Detection
• Early detection of radicalization
• Emotion Detection
• Extension/Generation of word nets
• Fake News Detection
• Gender Prediction from Text
• Geographical text classification
• Hate speech detection
• Irony detection
• Natural Language Inference
• Phoneme Recognition
• Rumour detection
• Script Event Prediction
• Semantic role labelling
• Sentence similarity analysis
• Sentiment Analysis
• Social risk prediction
• Story Ending prediction
• Text Classification
• Text Data Augmentation
• Topic Modelling
• Transliterated Text Retrieval
• Word-representation models