Kumar Ravi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Kumar Ravi has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Vadlamani Ravi
Center of Excellence in Analytics, Institute for Development and Research in Banking Technology, Castle Hills Road #1, Masab Tank, Hyderabad, 500057, India
11 shared publicationsB. Shivakrishna
Center of Excellence in Analytics, Institute for Development and Research in Banking Technology, Castle Hills Road No.1, Masab Tank, Hyderabad, 500057, India
1 shared publicationBoora Shiva Krishna
1 shared publication- Chandan Gautam
Indian Institute of Technology Indore
1 shared publication Lalit Mohan
IDRBT, Castle Hills, Masab Tank, Hyderabad India
1 shared publication- P. Sree Rama Krishna Prasad1 shared publication
Latest Publications
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 78-85
Article Citation Sentiment Analysis Using Deep Learning
We performed sentiment analysis on article citation sentences corpora bearing three polarities viz. positive, negative, and neutral. Due to scarcity of negative citation sentences, the dataset suffers from a huge class imbalance issue. To tackle this, we proposed an ensemble feature engineering method for deep learning, which uses embedding of text and its dependency relationships. The performance of deep learning models was compared with a support vector machine and logistic regression approach using bag of words. Experimental results show that deep learning can be used effectively for an imbalanced dataset by applying the proposed ensemble features. Statistical significance test indicates that one-hot supervised LSTM is statistically not different from the baseline methods for two datasets, one developed by us and the other taken from literature.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 78-85
Article Citation Sentiment Analysis Using Deep Learning
We performed sentiment analysis on article citation sentences corpora bearing three polarities viz. positive, negative, and neutral. Due to scarcity of negative citation sentences, the dataset suffers from a huge class imbalance issue. To tackle this, we proposed an ensemble feature engineering method for deep learning, which uses embedding of text and its dependency relationships. The performance of deep learning models was compared with a support vector machine and logistic regression approach using bag of words. Experimental results show that deep learning can be used effectively for an imbalanced dataset by applying the proposed ensemble features. Statistical significance test indicates that one-hot supervised LSTM is statistically not different from the baseline methods for two datasets, one developed by us and the other taken from literature.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 254-260
Irony Detection Using Neural Network Language Model, Psycholinguistic Features and Text Mining
Irony is a form of figurative language, which is often used to make fun of an entity. We employ paragraph vector to capture syntactic and semantic features of the figurative language to subsequently detect satiric and ironic content in a given text using data mining. We extract psycholinguistic features with the help of a tool called Linguistic Inquiry Word Count. In order to extract useful insights of what constitutes figurative language, we combined syntactic, semantic, and psycholinguistic features together. We demonstrated the effectiveness of the proposed methodology on two satiric news datasets and one ironic customer review dataset. The proposed approach outperformed on the state of the art results.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 254-260
Irony Detection Using Neural Network Language Model, Psycholinguistic Features and Text Mining
Irony is a form of figurative language, which is often used to make fun of an entity. We employ paragraph vector to capture syntactic and semantic features of the figurative language to subsequently detect satiric and ironic content in a given text using data mining. We extract psycholinguistic features with the help of a tool called Linguistic Inquiry Word Count. In order to extract useful insights of what constitutes figurative language, we combined syntactic, semantic, and psycholinguistic features together. We demonstrated the effectiveness of the proposed methodology on two satiric news datasets and one ironic customer review dataset. The proposed approach outperformed on the state of the art results.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 187-194
Sentiment Classification Using Paragraph Vector and Cognitive Big Data Semantics on Apache Spark
Apache Spark allows us to write a distributed version of any machine learning algorithm, which can be easily scaled up for a larger dataset on a cluster of commodity hardware. In this paper, we propose the hybridization of paragraph vector with distributed, parallel versions of well-known six machine learning techniques for sentiment analysis. We employed a distributed implementation of neural network language model to obtain paragraph vectors for a given corpus. On the paragraph vectors so obtained, we employed a host of distributed classification algorithms available in Apache Spark to perform sentiment classification. We considered two approaches viz. Bag-of-Words based document-term matrix (DTM) and hashing-trick based DTM as two baseline methods for comparison. We experimented with a movie review dataset of size 992 MB. Among the six classifiers employed, MLP turned out to be statistically the same as GBT and SVM, while it statistically significantly outperformed the rest of classifiers by yielding an area under of ROC curve (AUC) of 95.44%.
- 1 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 187-194
Sentiment Classification Using Paragraph Vector and Cognitive Big Data Semantics on Apache Spark
Apache Spark allows us to write a distributed version of any machine learning algorithm, which can be easily scaled up for a larger dataset on a cluster of commodity hardware. In this paper, we propose the hybridization of paragraph vector with distributed, parallel versions of well-known six machine learning techniques for sentiment analysis. We employed a distributed implementation of neural network language model to obtain paragraph vectors for a given corpus. On the paragraph vectors so obtained, we employed a host of distributed classification algorithms available in Apache Spark to perform sentiment classification. We considered two approaches viz. Bag-of-Words based document-term matrix (DTM) and hashing-trick based DTM as two baseline methods for comparison. We experimented with a movie review dataset of size 992 MB. Among the six classifiers employed, MLP turned out to be statistically the same as GBT and SVM, while it statistically significantly outperformed the rest of classifiers by yielding an area under of ROC curve (AUC) of 95.44%.
- 1 January 2018
- Published by Elsevier in Journal of Network and Computer Applications
- Vol. 102, 17-37
Analytics in/for cloud-an interdependence: A review
- 1 January 2018
- Published by Elsevier in Journal of Network and Computer Applications
- Vol. 102, 17-37
Analytics in/for cloud-an interdependence: A review
- 1 November 2017
- Published by Elsevier in Applied Soft Computing
- Vol. 60, 786-807
Fuzzy formal concept analysis based opinion mining for CRM in financial services
- 1 November 2017
- Published by Elsevier in Applied Soft Computing
- Vol. 60, 786-807
Fuzzy formal concept analysis based opinion mining for CRM in financial services
- 19 August 2017
- Published by Springer Nature
- p. 698-708
Online Clustering Based Concept Lattice Reduction
- 19 August 2017
- Published by Springer Nature
- p. 698-708
Online Clustering Based Concept Lattice Reduction
- 1 March 2017
- Published by Elsevier in Knowledge-Based Systems
- Vol. 120, 15-33
A novel automatic satire and irony detection using ensembled feature selection and data mining
- 1 March 2017
- Published by Elsevier in Knowledge-Based Systems
- Vol. 120, 15-33
A novel automatic satire and irony detection using ensembled feature selection and data mining
- 1 March 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 641-645
Sentiment classification of Hinglish text
In order to determine the sentiment polarity of Hinglish text written in Roman script, we experimented with different combinations of feature selection methods and a host of classifiers using term frequency-inverse document frequency feature representation. We carried out in total 840 experiments in order to determine the best classifiers for sentiment expressed in the news and Facebook comments written in Hinglish. We concluded that a triumvirate of term frequency-inverse document frequency-based feature representation, gain ratio based feature selection, and Radial Basis Function Neural Network as the best combination to classify sentiment expressed in the Hinglish text.
- 1 March 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 641-645
Sentiment classification of Hinglish text
In order to determine the sentiment polarity of Hinglish text written in Roman script, we experimented with different combinations of feature selection methods and a host of classifiers using term frequency-inverse document frequency feature representation. We carried out in total 840 experiments in order to determine the best classifiers for sentiment expressed in the news and Facebook comments written in Hinglish. We concluded that a triumvirate of term frequency-inverse document frequency-based feature representation, gain ratio based feature selection, and Radial Basis Function Neural Network as the best combination to classify sentiment expressed in the Hinglish text.
- 1 March 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 511-516
A novel deep learning architecture for sentiment classification
Evolution of plethora of e-commerce sites resulted in fierce competition among their providers. In order to acquire new and retain existing customers, various producers and market managers effectively employ online feedback analytics tools. Most of the online feedback analysis tools are built using sentiment analysis models. Sentiment analysis evolved in the last one and half decades for review mining process. An important sub-task of sentiment analysis called sentiment classification is used mainly to decide whether a written review is expressing either positive or negative sentiment towards a target entity. In order to have better sentiment classification accuracy, we proposed a hybrid deep learning architecture, which is a hybrid of a two layered Restricted Boltzmann Machine and a Probabilistic Neural Network. The proposed approach yielded better accuracy for five different datasets compared to the state-of-the-art.
- 1 March 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 511-516
A novel deep learning architecture for sentiment classification
Evolution of plethora of e-commerce sites resulted in fierce competition among their providers. In order to acquire new and retain existing customers, various producers and market managers effectively employ online feedback analytics tools. Most of the online feedback analysis tools are built using sentiment analysis models. Sentiment analysis evolved in the last one and half decades for review mining process. An important sub-task of sentiment analysis called sentiment classification is used mainly to decide whether a written review is expressing either positive or negative sentiment towards a target entity. In order to have better sentiment classification accuracy, we proposed a hybrid deep learning architecture, which is a hybrid of a two layered Restricted Boltzmann Machine and a Probabilistic Neural Network. The proposed approach yielded better accuracy for five different datasets compared to the state-of-the-art.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 10, 1-6
Sentiment analysis applied to Educational Sector
Sentiment analysis found various applications in banking, financial, service, and insurance sector. In this regard, we proposed to analyze customer reviews on the basis of sentiment score. We analyzed a set of credible text reviews collected on 270 training programmes posted by 2688 participants in an organization. In order to evaluate the efficacy of the proposed approach, we computed correlation coefficient between sentiment score obtained from the unstructured reviews and the numerical rating assigned by the participants. Further, we employed visualization analytics to get insights into different aspects of the programmes.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 10, 1-6
Sentiment analysis applied to Educational Sector
Sentiment analysis found various applications in banking, financial, service, and insurance sector. In this regard, we proposed to analyze customer reviews on the basis of sentiment score. We analyzed a set of credible text reviews collected on 270 training programmes posted by 2688 participants in an organization. In order to evaluate the efficacy of the proposed approach, we computed correlation coefficient between sentiment score obtained from the unstructured reviews and the numerical rating assigned by the participants. Further, we employed visualization analytics to get insights into different aspects of the programmes.