Papers by Shri Ramya Perumal
Social media and online forums are the communication mediums through which people can share their... more Social media and online forums are the communication mediums through which people can share their opinions, thoughts, ideas, views, etc. It will be helpful for a common man to understand things from different perspectives for making a crucial decision. It generates data in different varieties like text, image, audio, video, etc. The text data possess valuable information but it is hard to extract it as the data are in an unstructured format. It is the majorly contributed source in social media. The innovation of text mining is used to explore the hidden pattern and classify the data into their categories. Our proposed system uses IMDB movie review as a dataset which consists of positive class and negative class having 1000 text reviews in each class. Our proposed system employs word2vec for representing features in a text corpus and uses machine learning algorithms viz. K Nearest Neighbor, Logistic regression, and linear support vector machine to classify the text reviews. Adjective and adverb words are the two significant features that qualify nouns and verbs in the texts. These features are dependent on sentiment classification. These informative features could be extracted by integrating wordnet with a lexical database. Redundant and Irrelevant features are considered noise that could be ignored by using effective feature optimization techniques such as genetic algorithms. The proposed work provides remarkable performance in terms of accuracy 75%, precision 75%, recall 75%, and f1-score 75%.
24TH TOPICAL CONFERENCE ON RADIO-FREQUENCY POWER IN PLASMAS, 2022
Abstract. Nowadays social media plays a significant role in all sorts of our activities ranging f... more Abstract. Nowadays social media plays a significant role in all sorts of our activities ranging from analysing the attitude of a
person for the job, getting opinions towards buying a product, acting as a forum for exchanging thoughts about the current events of
various domains, creating awareness to the public about the natural calamities, educating the public about the fraudulent news
spread by the fakers, initiating the young aspirant to protest against any societal issues, etc. Grasping the opinions shared by the
experienced people towards a product, film, event, news, or politics like any subject of matter is one among the worth noting
applications for a common man. It extends its application to making decisions about our day-to-day activities. The text reviews
consist of enormous, sparse, non-uniform distribution of words represented as features. Text mining is the backend process for
those applications. It includes techniques such as feature representation, sentiment classification, feature optimization, etc.
Analysing the opinions suggested by the experienced people as positive and negative reviews is a challenging process and it is the
baseline of our work. This paper contributes to the related processes involved in analysing the sentiments from the text reviews
and accurately classifying them based on their polarity. In the proposed work, we particularly focus on feature representation
techniques that have a major effect on enhancing the performance of sentiment classification. We explore different feature
representation models such as TF-IDF vectorizer, word2vec vectorizer, and glove vectorizer as these word embedding models are
interpreting the words and their syntactic and semantic relationships differently from the corpus. Also, we employ machine learning
algorithms and a deep convolution neural network to perform comparative studies in classifying the sentiments. The word2vec in
combination with Deep Convolution Neural Network provides the accuracy of 85.7%, precision of 84.4%, recall of 87%, and F-
measure of 85.7% compared to other models.
Uploads
Papers by Shri Ramya Perumal
person for the job, getting opinions towards buying a product, acting as a forum for exchanging thoughts about the current events of
various domains, creating awareness to the public about the natural calamities, educating the public about the fraudulent news
spread by the fakers, initiating the young aspirant to protest against any societal issues, etc. Grasping the opinions shared by the
experienced people towards a product, film, event, news, or politics like any subject of matter is one among the worth noting
applications for a common man. It extends its application to making decisions about our day-to-day activities. The text reviews
consist of enormous, sparse, non-uniform distribution of words represented as features. Text mining is the backend process for
those applications. It includes techniques such as feature representation, sentiment classification, feature optimization, etc.
Analysing the opinions suggested by the experienced people as positive and negative reviews is a challenging process and it is the
baseline of our work. This paper contributes to the related processes involved in analysing the sentiments from the text reviews
and accurately classifying them based on their polarity. In the proposed work, we particularly focus on feature representation
techniques that have a major effect on enhancing the performance of sentiment classification. We explore different feature
representation models such as TF-IDF vectorizer, word2vec vectorizer, and glove vectorizer as these word embedding models are
interpreting the words and their syntactic and semantic relationships differently from the corpus. Also, we employ machine learning
algorithms and a deep convolution neural network to perform comparative studies in classifying the sentiments. The word2vec in
combination with Deep Convolution Neural Network provides the accuracy of 85.7%, precision of 84.4%, recall of 87%, and F-
measure of 85.7% compared to other models.
person for the job, getting opinions towards buying a product, acting as a forum for exchanging thoughts about the current events of
various domains, creating awareness to the public about the natural calamities, educating the public about the fraudulent news
spread by the fakers, initiating the young aspirant to protest against any societal issues, etc. Grasping the opinions shared by the
experienced people towards a product, film, event, news, or politics like any subject of matter is one among the worth noting
applications for a common man. It extends its application to making decisions about our day-to-day activities. The text reviews
consist of enormous, sparse, non-uniform distribution of words represented as features. Text mining is the backend process for
those applications. It includes techniques such as feature representation, sentiment classification, feature optimization, etc.
Analysing the opinions suggested by the experienced people as positive and negative reviews is a challenging process and it is the
baseline of our work. This paper contributes to the related processes involved in analysing the sentiments from the text reviews
and accurately classifying them based on their polarity. In the proposed work, we particularly focus on feature representation
techniques that have a major effect on enhancing the performance of sentiment classification. We explore different feature
representation models such as TF-IDF vectorizer, word2vec vectorizer, and glove vectorizer as these word embedding models are
interpreting the words and their syntactic and semantic relationships differently from the corpus. Also, we employ machine learning
algorithms and a deep convolution neural network to perform comparative studies in classifying the sentiments. The word2vec in
combination with Deep Convolution Neural Network provides the accuracy of 85.7%, precision of 84.4%, recall of 87%, and F-
measure of 85.7% compared to other models.