A Hybrid Model Integrating Adaboost Approach for Sentimental Analysis of Airline Tweets

Abstract

Sentimental Analysis has grown as a significant opinion strategy in the field of online media due to quick information development and internet technologies. This research will play an important role for recommendation of best airline for Indian passengers to prefer the appropriate airline for their journey and also useful for the Indian ministry of aviation. In this study we have gathered different tiny texts called comments from different social media traveling websites using webharvy data fetcher scraping tool related to six top rated Indian airlines. The main problem with airline tweet SA (sentimental analysis) is determining the best sentiment classifier for appropriately classifying the tweets. VADER model has used sentiment ratings to connect lexical characteristics to emotion intensities. In this research, a Hybrid model integrated Adaboost approach (HMIAA) has proposed, which combines the basic learning classifier SVM with the forward-learning ensemble method Gradient Boosted Tree to form a single robust classifier or model, with the objective of improving SCT (sentimental classification technique) efficiency (performance) and accuracy. The findings reveal that the suggested hybrid approach integrating Adaboost technique outperforms other basic classifiers. After completion of sentimental analysis of all datasets we can recommend the passengers for the best airline.

A Systematic Review on Airlines Industries based on Sentiment Analysis and Topic Modeling

“…Firstly, methods that lack training data are mainly due to language barriers and airline dependency [ [39], [48], [86], [74]]. Travelers often feel more compelled to put negative reviews, resulting in small, imbalanced [ [26], [28], [50], [14]] training data. Secondly, lack of preprocessing [54], not conducting training with shortlisted feature sets [ [12], [58]] and utilization of entire feature space [ [27], [51]] while creating split trees epitomize limitations in training.…”

“…Finally, the lack of prudence in choosing the right metric to evaluate model performance [68] and inadequate evaluations [ [13], [56], [57], [87]] call for more attention from researchers in the vicinity of performance evaluation. Algorithms like: SVM [ [13], [58]], LR [28], SGD [48], NB [39] have shown great promise, with accuracies of 77%, 79%, 88%, 94% respectively. However, more robust language models: LSTM [59], BERT [54] still remain unexplored.…”

“…A new deep learning model, which successfully integrates different word integration with deep learning methods, was developed by Hasib et al [27] for evaluating data from six important US Airlines tweets, and for multi class sentiment analyzes, with 91% precision. Furthermore, Rajat et al [28] developed five distinct categorization methods for evaluating the emotions included within Indian Air Asia Service tweets. AdaBoost (Ensemble), which integrates many different algorithms to generate a strong predictor with the efficiency of 84.5% [29], is one of the most often used classification algorithms.…”

“…A basic diagram of logistic regression for classification of the customer review is illustrated in Figure 5. Yadu et al [28] carried out five different classification strategies for classifying the sentiment of Twitter messages: Decision Tree, Random Forest, SVM, Logistic Regression, and Naive Bayes. The authors have achieved the best accuracy of 79.53% in the case of the Logistic Regression classifier.…”

Leveraging Text Mining for Analyzing Students' Preferences in Computer Science and Language Courses

“…Applications of TM are widespread and diverse, including cancer research analysis [9], opinion analysis of digital banking applications [10], sentimental analysis [11,12] vaccine hesitancy studies [13], and analysis of information management systems research topics [14]. Other applications include Twitter content sharing studies [15], text classification [16], database vulnerability identification [17], Business Intelligence article reviews [18], Peruvian professional CV analysis [19], and construction sector research [20].…”