Big Data Recommendation Research Based on Travel Consumer Sentiment Analysis

Zhu, Yuejian

doi:10.3389/fpsyg.2022.857292

Cited by 9 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e new media form of tourism has been widely recognized. An increasing number of tourists express their feelings and attitudes during travel through the Internet, showing their travel process and expressing their travel feelings in the form of online travel notes and comments [21,22]. ese network texts are authentic and extensive and play an important role in shaping the image of tourist destinations and providing a reference for tourists [23].…”

Section: Discussionmentioning

confidence: 99%

Analysis of Public Big Data Management under Text Analysis

Zhu

Kan

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Based on text analysis, public big data management is studied. The public data management of Mount Wutai tourism network travel notes is discussed. The positive, neutral, and negative effects of the naive Bayesian classification model and decision tree classification model on the tourism sentiment attitude of Mount Wutai are compared. The relationship between tourism resources, tourism facilities, tourism services, tourism environment, and tourism sentiment and attitude of Wutai Mountain is analyzed. The results show that the true positive rate, true negative rate, and F-measure of the Bayesian decision tree classifier to classify positive text are 86.64%, 81.27%, and 84.62%, respectively. The true positive rate for neutral text is 82.05%, the true negative rate is 78.89%, and the F-measure is 77.11%. The true positive rate for negative text is 83.67%, the true negative rate is 98.29%, and the F-measure is 82.83%. The Bayesian decision tree classifier can evaluate positive and negative texts better than neutral texts. The true positive rate of the C4.5 decision tree classifier for positive text is 91.44%, the true negative rate is 86.57%, and the F-measure is 89.45%. The true positive rate for neutral text is 90.17%, the true negative rate is 83.28%, and the F-measure is 84.06%. The true positive rate for negative text is 91.84%, the true negative rate is 99.05%, and the F-measure is 90.91%. The decision tree classifier has a better evaluation effect on positive and negative texts than on neutral texts. The ROC curve of the evaluation effect of the two classifiers shows that the evaluation effect of the two classifiers has a better evaluation effect on positive text than that of the neutral and negative texts, and the evaluation effect of the C4.5 decision tree classifier is better than that of the Bayesian classifier. The promotion degree of tourism resources and facilities in forwarding online travel notes is obviously higher, and there is a high correlation between tourism resources and facilities and forward online travel notes. In negative online travel notes, the promotion degree of tourism service and tourism environment is high, and the correlation between tourism service and tourism environment and negative online travel notes is high. In summary, improving the quality of tourism services and the tourism environment of Mount Wutai scenic spots can better enhance the recognition and satisfaction of tourists with Mount Wutai tourism.

show abstract

Section: Discussionmentioning

confidence: 99%

Analysis of Public Big Data Management under Text Analysis

Zhu

Kan

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Many studies in the tourism and hospitality sectors have focused on travel sentiment analysis. Tese studies, however, focused on assessing the opinions posted by tourists on multiple platforms using sentiment analysis and opinion-mining techniques [27][28][29]. Because of this, despite their semantic similarity, the travel sentiment examined in this paper and the sentiment conveyed in reviews are not the same.…”

Section: Literature Reviewmentioning

confidence: 99%

Forecasting Travel Sentiment under the Shock Effects of COVID-19 and Vaccination Using Grey Prediction Models

Lee

Kong

2023

Journal of Mathematics

View full text Add to dashboard Cite

The tourism industry has become a major contributor to the economic growth. However, because of the outbreak of the coronavirus disease (COVID-19) pandemic, the year 2020 became an extremely difficult year for the global tourism industry. Since the development of the tourism industry depends largely on changes in travel sentiment, it is important to analyze these changes in light of the pandemic. To determine the development trends of travel sentiment, a hybrid grey prediction model was used to predict travel sentiment globally and in the top 10 destination countries considering the shock effect of COVID-19 and vaccination. The results showed that the grey prediction models integrated with residual modification model contributed to improving the prediction accuracy. In addition, COVID-19 and vaccination were found to have opposite effects on travel sentiment. Based on the predictions, governments should strengthen pandemic prevention and control and administer vaccines to restore travel sentiment and promote tourism recovery.

show abstract

“…However, this approach cannot apply to the sentiment analysis of continuous and multi-dimensional information. Yuan (2022) proposed an improved support vector machine (SVM) algorithm that analyzed travellers' sentiments using linear classification and kernel functions and used a Hadoop distributed file system. However, the method was limited to analyzing the travellers' emotions.…”

Section: Related Workmentioning

confidence: 99%

Sentiment Classification of Social Network Text Based on AT-BiLSTM Model in a Big Data Environment

Liu

2023

International Journal of Information Technologies and Systems Approach

View full text Add to dashboard Cite

To tackle the challenge of ineffective sentiment prediction using current sentiment classification methods, this paper introduces a method social network text sentiment classification. The method leverages a bidirectional short and long-term memory model (AT-BiLSTM), specifically designed for a big data environment. First, a vectorized representation of text is realized by introducing a pre-trained BERT model, and the classification results are dynamically adjusted according to the semantic information of the words. Then, the BiLSTM combined with the attention mechanism performs aspect-level sentiment analysis, and the corresponding model AT-BiLSTM is formulated. Finally, the BERT model randomly selects input tags for information masking and pre-trains the proposed model. The proposed method was evaluated against three alternative methods using an identical dataset. The results show that the novel method achieved the highest accuracy, recall, and F1-score, reaching 93.72%, 93.91%, and 92.38%, respectively. Consequently, the proposed method demonstrates superior performance compared to the other three methods evaluated.

show abstract

Big Data Recommendation Research Based on Travel Consumer Sentiment Analysis

Cited by 9 publications

References 28 publications

Analysis of Public Big Data Management under Text Analysis

Analysis of Public Big Data Management under Text Analysis

Forecasting Travel Sentiment under the Shock Effects of COVID-19 and Vaccination Using Grey Prediction Models

Sentiment Classification of Social Network Text Based on AT-BiLSTM Model in a Big Data Environment

Contact Info

Product

Resources

About