P
Prathusha Kameswara Sarma
Researcher at University of Wisconsin-Madison
Publications - 18
Citations - 313
Prathusha Kameswara Sarma is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Sentiment analysis & Word (computer architecture). The author has an hindex of 7, co-authored 16 publications receiving 158 citations. Previous affiliations of Prathusha Kameswara Sarma include State University of New York System.
Papers
More filters
Journal ArticleDOI
Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis
TL;DR: A novel model, the Interaction Canonical Correlation Network (ICCN), is proposed, which learns correlations between all three modes via deep canonical correlation analysis (DCCA) and the proposed embeddings are tested on several benchmark datasets and against other state-of-the-art multimodal embedding algorithms.
Proceedings ArticleDOI
Domain Adapted Word Embeddings for Improved Sentiment Classification
TL;DR: Evaluation results on sentiment classification tasks show that the DA embeddings substantially outperform both generic, DS embedDings when used as input features to standard or state-of-the-art sentence encoding algorithms for classification.
Journal ArticleDOI
Detecting Recovery Problems Just in Time: Application of Automated Linguistic Analysis and Supervised Machine Learning to an Online Substance Abuse Forum.
Rachel Kornfield,Prathusha Kameswara Sarma,Dhavan V. Shah,Fiona McTavish,Gina Landucci,Klaren Pe-Romashko,David H. Gustafson +6 more
TL;DR: This paper aimed to investigate whether computational linguistics and supervised machine learning can be applied to successfully flag, in real time, those discussion forum messages that moderators find most concerning, and differences in language use can distinguish messages disclosing recovery problems from other message types.
Posted Content
Multi-modal Sentiment Analysis using Deep Canonical Correlation Analysis
TL;DR: This paper learns multi-modal embeddings from text, audio, and video views/modes of data in order to improve upon down-stream sentiment classification and posit that this highly optimized algorithm dominates over the contribution of other views, though each view does contribute to the final result.
Proceedings ArticleDOI
Multi-modal sentiment analysis using deep canonical correlation analysis
TL;DR: This paper used Deep Canonical Correlation Analysis (DCCA) to learn multi-modal embeddings from text, audio, and video views/modes of data in order to improve upon down-stream sentiment classification.