Projects
MULTILINGUAL NGRAM-BASED CONVOLUTIONAL NETWORK FOR ASPECT CATEGORY DETECTION IN ONLINE REVIEWS [JAN 2022 - APR 2022]
Relation classifier with new information on entity embeddings utilizing Pre-trained BERT. Over the state-of-the-art strategy, this suggested model achieves significant performance on the KnowldgeNet relational dataset.
Multilingual Reviews Aspect Category
KNOWLEDGE DISTILLATION : AGGRESSION DETECTION USING MINI BERT [JAN 2022 - APR 2022]
The knowledge is transferred from the BERT base to mini BERT (3-layers) using knowledge distillation, which is 7.5x smaller and 9.4x faster on inference.
Knowledge Distillation Aggression detection BERT NLP
KNOWLDGENET RELATIONSHIP CLASSIFICATION USING A PRE-TRAINED MODEL [JAN 2022 - APR 2022]
Relation classifier with new information on entity embeddings utilizing Pre-trained BERT. Over the state-of-the-art strategy, this suggested model achieves significant performance on the KnowldgeNet relational dataset.
Relationship classification Entity Information NLP
ANALYSIS OF AUTHOR’S ABUSIVE BEHAVIOUR COMMUNITY ON TWITTER [AUG 2021 - NOV 2021]
This project briefly analyzes the author’s Abusive Behavior Network (ABN) by comparing it to the Normal Behavior Network (NBN). For analysis, the report uses social network analysis measures and effectively concludes that ABN has a densified network, information has spread rapidly, and much more. It also identifies the topics the author has been abusive on. This study will undoubtedly aid in distinguishing between the author’s abusive and normal communities.
Author profiling Hate speech Community analysis SNA
CONTEXTUAL JOURNAL RECOMMENDATION AND QUERY SEARCH ENGINE USING WORD EMBEDDING [AUG 2021 - OCT 2021]
The proposed methodology will aid aspiring researchers in determining which journal to submit their work to for publication.
Context vector Recommendation system NLP
POLARITY BASED SARCASM DETECTION USING SEMIGRAPH [AUG 2020 - MAR 2021]
A variation of the semigraph is suggested in the pattern-relatedness of the text document. The proposed method is to obtain the sarcastic and non-sarcastic polarity scores of a document using a semigraph.
Sarcasm detection Sentiment analysis Semigraph NLP
THEMATIC CONTEXT VECTOR ASSOCIATION BASED ON EVENT UNCERTAINTY FOR TWITTER [JUL 2020 - AUG 2020]
In this project, keywords are extracted using contextual events with the help of data association. The thematic context vectors for events are identified using uncertainty principle in the proposed system. The system is tested on the twitter COVID-19 dataset and proves to be effective. The system extracts event specific thematic context vectors from the test dataset and ranks them. The extracted thematic context vectors are used for the clustering of contextual thematic vectors which improves silhouette coefficient by 0.5% than state of art methods namely TF and TF-IDF. The thematic context vector can be used in other applications like Cyber bullying, sarcasm detection, figurative language detection etc.
Context vector Twitter NLP
EFFECTIVE FEATURE EXTRACTION FOR INTRUSION DETECTION SYSTEM USING NON-NEGATIVE MATRIX FACTORIZATION AND UNIVARIATE ANALYSIS [JUL 2020 - NOV 2020]
The proposed model is implemented on three publicly available datasets, which gives significant improvement. According to recent research, the proposed model has achieved 4.66% and 0.39% with respective NSL-KDD and CICD 2017.
Effective Feature extraction IDS
IDENTIFICATION OF CERTAIN ENTITIES OF EACH EVENTS FROM TWITTER [JUL 2020 - JUL 2020]
This project proposed a method to derive uncertainty of entities in events with respect to context. The proposed method has been applied to the news dataset created using Twitter data and proves to be useful for identification of important events and entities from the document.
Twitter events NLP
EXPLORING TOPICS DISCUSSED IN WHATSAPP WITH SENTIMENT AND STATISTICAL ANALYSIS [JUL 2020 - JUL 2020]
Worked on a statistical analysis of the WhatsApp group chat. This will answer some general questions. Also, we build a sentiment analysis of personal and group chats. The sentiment of WhatsApp chat will give user-wise sentiment analysis. This will help you get the user's overall emotion during the chat.
Statistical analysis Sentiment analysis Topic modeling NLP