Hardwik Sharma - Academia.edu (original) (raw)
Uploads
Papers by Hardwik Sharma
This research paper aims to explore the effectiveness of machine learning algorithms in analyzing... more This research paper aims to explore the effectiveness of machine learning algorithms in analyzing sentiment on Twitter. The study utilizes a dataset of tweets collected from various sources, which were then preprocessed to remove noise and irrelevant data [4, 5]. To categorize the tweets as positive, negative, or neutral, a number of machine learning techniques were used, such as logistic regression and Naive Bayesian [1]. The efficiency of these algorithms is also assessed in the study using a number of criteria, including accuracy, precision, recall, and F1 score. The results indicate that machine learning algorithms are effective in analyzing sentiment on Twitter, with Naive Bayes providing the best performance [18]. The results of this study have significant ramifications for companies and organizations looking to track consumer opinion of their goods or services [7]. This paper examines the problem of analyzing sentiment in Twitter by examining the tweets' expressed sentiments-whether they be favourable, negative, or neutral. Natural language processing methods will be used to analyze the messages that are tweeted.
International Journal for Research in Applied Science and Engineering Technology, 2021
Nowadays, social networking sites are at the boom, therefore great deal of knowledge is generated... more Nowadays, social networking sites are at the boom, therefore great deal of knowledge is generated. Millions of people are sharing their views daily on twitter. This paper contributes to the sentiment analysis for customers' review classification which is useful to analyze the knowledge within the sort of the amount of tweets where opinions are highly unstructured and are either positive or negative, or somewhere in between of those two. For this we first pre-processed the data set, because of the unstructured tweets; the technique of pre-processing the raw data is Removal of punctuation, Removal of common words (Stop words), Normalization of Words and lastly vectorisation. thereafter applied machine learning based classification algorithms namely: 1. Naïve Bayes Algorithm 2. Logistic Regression Algorithm 3. Decision tree Algorithm 4. Random Forest Algorithm. The Naive Bayes algorithm was for simple classification and while Logistic Regression, Decision Tree and Random Forest Algorithm was used for Standardization. We also conclude that through this , that Logistic regression algorithm provides highest accuracy of 95% whereas Decision Tree and Logistic Regression give accuracy of 93% and 94% respectively. I.
This research paper aims to explore the effectiveness of machine learning algorithms in analyzing... more This research paper aims to explore the effectiveness of machine learning algorithms in analyzing sentiment on Twitter. The study utilizes a dataset of tweets collected from various sources, which were then preprocessed to remove noise and irrelevant data [4, 5]. To categorize the tweets as positive, negative, or neutral, a number of machine learning techniques were used, such as logistic regression and Naive Bayesian [1]. The efficiency of these algorithms is also assessed in the study using a number of criteria, including accuracy, precision, recall, and F1 score. The results indicate that machine learning algorithms are effective in analyzing sentiment on Twitter, with Naive Bayes providing the best performance [18]. The results of this study have significant ramifications for companies and organizations looking to track consumer opinion of their goods or services [7]. This paper examines the problem of analyzing sentiment in Twitter by examining the tweets' expressed sentiments-whether they be favourable, negative, or neutral. Natural language processing methods will be used to analyze the messages that are tweeted.
International Journal for Research in Applied Science and Engineering Technology, 2021
Nowadays, social networking sites are at the boom, therefore great deal of knowledge is generated... more Nowadays, social networking sites are at the boom, therefore great deal of knowledge is generated. Millions of people are sharing their views daily on twitter. This paper contributes to the sentiment analysis for customers' review classification which is useful to analyze the knowledge within the sort of the amount of tweets where opinions are highly unstructured and are either positive or negative, or somewhere in between of those two. For this we first pre-processed the data set, because of the unstructured tweets; the technique of pre-processing the raw data is Removal of punctuation, Removal of common words (Stop words), Normalization of Words and lastly vectorisation. thereafter applied machine learning based classification algorithms namely: 1. Naïve Bayes Algorithm 2. Logistic Regression Algorithm 3. Decision tree Algorithm 4. Random Forest Algorithm. The Naive Bayes algorithm was for simple classification and while Logistic Regression, Decision Tree and Random Forest Algorithm was used for Standardization. We also conclude that through this , that Logistic regression algorithm provides highest accuracy of 95% whereas Decision Tree and Logistic Regression give accuracy of 93% and 94% respectively. I.