A5040613229- Topic Modeling
- Sentiment Analysis and Opinion Mining
- Natural Language Processing Techniques
- Advanced Text Analysis Techniques
- Music and Audio Processing
- Speech and Audio Processing
- Mental Health via Writing
- Biomedical Text Mining and Ontologies
- Music Technology and Sound Studies
- Mental Health Treatment and Access
- Maternal Mental Health During Pregnancy and Postpartum
- Text and Document Classification Technologies
- Health disparities and outcomes
- Bioinformatics and Genomic Networks
- Authorship Attribution and Profiling
- Food Security and Health in Diverse Populations
- Suicide and Self-Harm Studies
- Spam and Phishing Detection
- Gene expression and cancer classification
- Health Literacy and Information Accessibility
- Attachment and Relationship Dynamics
- Neural Networks and Applications
- Translation Studies and Practices
- Treatment of Major Depression
- Semantic Web and Ontologies
Weill Cornell Medicine
2021-2024
Cornell University
2021-2024
Nara Institute of Science and Technology
2024
University of York
2024
The University of Texas Health Science Center at Houston
2016-2021
Jadavpur University
2013-2018
National Institute of Technology Agartala
2012
Sentiment analysis is essential in many real-world applications such as stance detection, review analysis, recommendation system, and so on. becomes more difficult when the data noisy collected from social media. India a multilingual country; people use than one languages to communicate within themselves. The switching between called code-switching or code-mixing, depending upon type of mixing. This paper presents overview shared task on sentiment code-mixed pairs Hindi-English...
Abstract A scholarly recommendation system is an important tool for identifying prior and related resources such as literature, datasets, grants, collaborators. well-designed recommender significantly saves the time of researchers can provide information that would not otherwise be considered. The usefulness recommendations, especially literature has been established by widespread acceptance web search engines CiteSeerX, Google Scholar, Semantic Scholar. This article discusses different...
Abstract It is a growing trend among researchers to make their data publicly available for experimental reproducibility and reusability. Sharing with fellow helps in increasing the visibility of work. On other hand, there are who inhibited by lack resources. To overcome this challenge, many repositories knowledge bases have been established date ease sharing. Further, past two decades, has an exponential increase number datasets added these dataset repositories. However, most...
Abstract Objectives Social support (SS) and social isolation (SI) are determinants of health (SDOH) associated with psychiatric outcomes. In electronic records (EHRs), individual-level SS/SI is typically documented in narrative clinical notes rather than as structured coded data. Natural language processing (NLP) algorithms can automate the otherwise labor-intensive process extraction such information. Materials Methods Psychiatric encounter from Mount Sinai Health System (MSHS, n = 300)...
Selection of the optimal learning rate for training neural networks has often been a matter concern machine community. The existing rates are dependent on multiple scaling factors. This paper proposes Cost-Responsive Learning (CoRL) which does not require manual hyper-parameter tuning. It maintains linear relationship with prediction error network. is expected to offer lowest at global minima, and higher elsewhere. Hence, number proportional used as rate, subject constraint that within an...
The fast upswing of online reviews and their sentiments on the Web became very useful information to people. Thus, opinion/sentiment mining has been adopted as a subject increasingly research interest in recent years. Being participant Shared Task Challenge, we have developed Conditional Random Field based system accomplish Aspect Based Sentiment Analysis task. aspect term sentence is defined target entity. present identifies term, categories from Laptop Restaurants review datasets provided...
Background: Social support (SS) and social isolation (SI) are determinants of health (SDOH) associated with psychiatric outcomes. In electronic records (EHRs), individual-level SS/SI is typically documented as narrative clinical notes rather than structured coded data. Natural language processing (NLP) algorithms can automate the otherwise labor-intensive process data extraction. Data Methods: Psychiatric encounter from Mount Sinai Health System (MSHS, n=300) Weill Cornell Medicine (WCM,...
The complex word identification task refers to the process of identifying difficult words in a sentence from perspective readers belonging specific target audience.This has immense importance field lexical simplification.Lexical simplification helps improving readability texts consisting challenging words.As participant SemEval-2016: Task 11 shared task, we developed two systems using various and semantic features identify words, one Naïve Bayes another based on Random Forest Classifiers.The...
We describe the system submitted to SemEval-2016 for detecting stance in tweets (Task 6, Subtask A).One of main goals detection is automatically determine a tweet towards specific target as 'FAVOR', 'AGAINST', or 'NONE'.We developed supervised using Support Vector Machines identify by analyzing various lexical and semantic features.The average F1 score achieved our 60.60.
Objective Evidence suggests that high-quality health education and effective communication within the framework of social support hold significant potential in preventing postpartum depression. Yet, developing trustworthy engaging materials requires extensive expertise substantial resources. In light this, we propose an innovative approach involves leveraging natural language processing (NLP) to classify publicly accessible lay articles based on their relevance subject matter pregnancy...