Hotel Comment Emotion Classification Based on the MF-DFA and Partial Differential Equation Classifier
Due to the significant value that hotel reviews hold for both consumers and businesses, the development of an accurate sentiment classification method is crucial. By effectively distinguishing the authenticity of reviews, consumers can make informed decisions, and businesses can gain insights into c...
| Hlavní autoři: | , , |
|---|---|
| Médium: | Článek |
| Jazyk: | English |
| Vydáno: |
MDPI AG
2023-10-01
|
| Edice: | Fractal and Fractional |
| Témata: | |
| On-line přístup: | https://www.mdpi.com/2504-3110/7/10/744 |
| _version_ | 1827720913643110400 |
|---|---|
| author | Sangjie Duanzhu Jian Wang Cairang Jia |
| author_facet | Sangjie Duanzhu Jian Wang Cairang Jia |
| author_sort | Sangjie Duanzhu |
| collection | DOAJ |
| description | Due to the significant value that hotel reviews hold for both consumers and businesses, the development of an accurate sentiment classification method is crucial. By effectively distinguishing the authenticity of reviews, consumers can make informed decisions, and businesses can gain insights into customer feedback to improve their services and enhance overall competitiveness. In this paper, we propose a partial differential equation model based on phase-field for sentiment analysis in the field of hotel comment texts. The comment texts are converted into word vectors using the Word2Vec tool, and then we utilize the multifractal detrended fluctuation analysis (MF-DFA) model to extract the generalized Hurst exponent of the word vector time series to achieve dimensionality reduction of the word vector data. The dimensionality reduced data are represented in a two-dimensional computational domain, and the modified Allen–Cahn (AC) function is used to evolve the phase values of the data to obtain a stable nonlinear boundary, thereby achieving automatic classification of hotel comment texts. The experimental results show that the proposed method can effectively classify positive and negative samples and achieve excellent results in classification indicators. We compared our proposed classifier with traditional machine learning models and the results indicate that our method possesses a better performance. |
| first_indexed | 2024-03-10T21:13:57Z |
| format | Article |
| id | doaj.art-9f562e33f26f4ac4b4085336d5e577d6 |
| institution | Directory Open Access Journal |
| issn | 2504-3110 |
| language | English |
| last_indexed | 2024-03-10T21:13:57Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fractal and Fractional |
| spelling | doaj.art-9f562e33f26f4ac4b4085336d5e577d62023-11-19T16:34:41ZengMDPI AGFractal and Fractional2504-31102023-10-0171074410.3390/fractalfract7100744Hotel Comment Emotion Classification Based on the MF-DFA and Partial Differential Equation ClassifierSangjie Duanzhu0Jian Wang1Cairang Jia2School of Computer, Qinghai Normal University, Xining 810016, ChinaSchool of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Computer, Qinghai Normal University, Xining 810016, ChinaDue to the significant value that hotel reviews hold for both consumers and businesses, the development of an accurate sentiment classification method is crucial. By effectively distinguishing the authenticity of reviews, consumers can make informed decisions, and businesses can gain insights into customer feedback to improve their services and enhance overall competitiveness. In this paper, we propose a partial differential equation model based on phase-field for sentiment analysis in the field of hotel comment texts. The comment texts are converted into word vectors using the Word2Vec tool, and then we utilize the multifractal detrended fluctuation analysis (MF-DFA) model to extract the generalized Hurst exponent of the word vector time series to achieve dimensionality reduction of the word vector data. The dimensionality reduced data are represented in a two-dimensional computational domain, and the modified Allen–Cahn (AC) function is used to evolve the phase values of the data to obtain a stable nonlinear boundary, thereby achieving automatic classification of hotel comment texts. The experimental results show that the proposed method can effectively classify positive and negative samples and achieve excellent results in classification indicators. We compared our proposed classifier with traditional machine learning models and the results indicate that our method possesses a better performance.https://www.mdpi.com/2504-3110/7/10/744emotion classificationMF-DFAHurst exponentAllen–Cahn |
| spellingShingle | Sangjie Duanzhu Jian Wang Cairang Jia Hotel Comment Emotion Classification Based on the MF-DFA and Partial Differential Equation Classifier Fractal and Fractional emotion classification MF-DFA Hurst exponent Allen–Cahn |
| title | Hotel Comment Emotion Classification Based on the MF-DFA and Partial Differential Equation Classifier |
| title_full | Hotel Comment Emotion Classification Based on the MF-DFA and Partial Differential Equation Classifier |
| title_fullStr | Hotel Comment Emotion Classification Based on the MF-DFA and Partial Differential Equation Classifier |
| title_full_unstemmed | Hotel Comment Emotion Classification Based on the MF-DFA and Partial Differential Equation Classifier |
| title_short | Hotel Comment Emotion Classification Based on the MF-DFA and Partial Differential Equation Classifier |
| title_sort | hotel comment emotion classification based on the mf dfa and partial differential equation classifier |
| topic | emotion classification MF-DFA Hurst exponent Allen–Cahn |
| url | https://www.mdpi.com/2504-3110/7/10/744 |
| work_keys_str_mv | AT sangjieduanzhu hotelcommentemotionclassificationbasedonthemfdfaandpartialdifferentialequationclassifier AT jianwang hotelcommentemotionclassificationbasedonthemfdfaandpartialdifferentialequationclassifier AT cairangjia hotelcommentemotionclassificationbasedonthemfdfaandpartialdifferentialequationclassifier |