CC BY
0VII International Research and Practice Conference-Biennale «System Analysis in Economics-2022»
"HRONOECONOMICS". SPECIAL ISSUE
APPLICATION OF MACHINE LEARNING AND TEXT ANALYSIS IN MODELING THE IMPRESSION ECONOMY
ПРИМЕНЕНИЕ МАШИННОГО ОБУЧЕНИЯ И ТЕКСТОВОГО АНАЛИЗА В МОДЕЛИРОВАНИИ ЭКОНОМИКИ ВПЕЧАТЛЕНИЙ
Elena A. Fedorova 1 ORCID 0000-0002-3381-6116
Елена Анатольевна Федорова 1
1 Financial University under the Government of the Russian Federation 1 Финансовый университет при Правительстве Российской Федерации
Keywords: experience economy, text analysis, ML, hotel management, service industry
Today, the Russian tourism sector is developing rapidly: external factors and restrictions during the pandemic forced many tourists to look at trips and attractions in Russia differently. In the hotel business, the influence of the impression economy can now be most clearly traced.
The purpose of the study is to identify the influence of the factors of the economy of impressions (entertainment, education, aesthetics, escapism) and the economic component on the preferences in choosing hotels in the domestic tourism industry. The empirical base of the study includes 30926 reviews from the site tripadvisor.ru according to 1243 hotels in Russia for 2021-2022, divided by consumer estimates.
The research methodology includes a textual analysis of tourist reviews: counting the number of words and phrases in reviews, calculating word correlation, finding word connections using the word2vec embedding matrix, highlighting the most popular discussion topics based on the Latent Dirichlet allocation method (LDA) and evaluating tonality using the BERT transformer network.
The results of this study evaluate aspects of the basic model of the impression economy (aesthetics, escapism, entertainment, and education) and adapt the model for the domestic tourism and hospitality sector, adding relevant aspects (recommendations and economics). According to the results of a quantitative assessment of the aspects of the expanded model of the impression economy, it was revealed that the aesthetic aspect is decisive for people when evaluating hotels, and the aspects of entertainment and education, expressed indirectly, although of high importance, but not as much as the aesthetic parameters. The economic component, the price-quality ratio and the overall cost assessment also stands out in the main topics, but hotel reviews focus on it to a lesser
Ключевые слова: экономика впечатлений, текстовый анализ, машинное обучение, управление отелями, сфера услуг
Сегодня российская туристическая сфера бурно развивается: Внешние факторы и ограничения в период пандемии заставили многих туристов иначе взглянуть на поездки и достопримечательности в России. В гостиничном бизнесе сейчас наиболее явно можно проследить и влияние экономики впечатлений.
Цель исследования - выявить влияние факторов экономики впечатлений (развлечение, образование, эстетика, эскапизм) и экономической составляющей на предпочтения в выборе отелей в отечественной туристической отрасли. Эмпирическая база исследования включает 30926 отзывов с сайта tripadvisor.ru по 1243 отелям России за 2021-2022 года, разделенных по оценкам потребителей.
Методология исследования включает текстовый анализ отзывов туристов: подсчет частности слов и словосочетаний в отзывах, расчет корреляции слов, нахождение связей слов при помощи матрицы эмбеддингов word2vec, выделение наиболее популярных тем обсуждений на основе метода латентного размещения дирихле (Latent Dirichlet allocation, LDA) и оценку тональности при помощи сети-трансформера BERT. Результаты данного исследования оценивают аспекты базовой модели экономики впечатлений (эстетика, эскапизм, развлечение и образование) и адаптируют модель для отечественной сферы туризма и гостеприимства, добавляя релевантными аспектами (рекомендации и экономики). По результатам количественной оценки аспектов расширенной модели экономики впечатлений было выявлено, что эстетический аспект является определяющим для людей при оценке отелей, а аспекты развлечения и образования, выраженные косвенно, хоть и имеют высокую значимость, но не настолько, как эстетические параметры. Экономическая составляющая, прежде всего соотношение «цена-качество» и общая оценка стоимости также выделяется
_90_
VIIМеждународная научно-практическая конференция «Системный анализ в экономике-2022» _«ХРОНОЭКОНОМИКА». СПЕЦВЫПУСК_
Fedorova E. A.
Application of Machine Learning and Text Analysis in Modeling the Impression Economy
extent. This is the first time such a study of the evaluation of aspects of the impression economy model for the tourism industry in Russia.
в основных тематиках, однако обзоры отелей фокусируются на ней в меньшей степени. Подобное исследование оценки аспектов модели экономики впечатлений для туристической отрасли в России впервые.
References / Библиография
1. Cheng B., Wang M., Morch A., Chen. N, Kinshuk, Spector M. 2014. Research on e-learning in theworkplace 2000-2012: a bib-liometric analysis of the literature. Educational Research Review 11: 56-72. D0I:10.1016/j.edurev.2014.01.001.
2. Chirakranont R., Sakdiyakorn M. 2022. Conceptualizing meaningful tourism experiences: Case study of a small craft beer breweryin Thailand. Journal of Destination Marketing & Management 23: 100691.
3. Claudia M., Hyungsoo T., Rauschnabel P.A. 2018. Computers in Human Behavior Determining visitor engagement throughaugmented reality at science festivals: An experience economy perspective. Computers in Human Behavior. Elsevier Ltd 82: 44-53.doi: 10.1016/j.chb.2017.12.043.
4. Devlin J. Chang M., Lee K., Toutanova K. 2018. Bert: Pre-train-ing of deep bidirectional transformers for language understand-ing.arXiv preprint:1810.04805.
5. Hinton G.E., Roweis S.T. 2002. Stochastic Neighbor Embedding, Advances in Neural Information Processing Systems. The MITPress, Cambridge: 857-864.
6. Hwang J., Ok S. 2015. Journal of Destination Marketing & Management The antecedents and consequences of well-beingper-ception: An application of the experience economy to golf tournament tourists. Elsevier Ltd 4: 248-257. doi:10.1016/j.jdmm.2015.09.002
7. Le T., Jeong D. 2017. NLP-based approach to semantic classification of heterogeneous transportation asset data terminol-ogy.Journal of Computing in Civil Engineering 31(6): 1-13. 10.1061/(ASCE)CP. 1943-5487.00007010401 7057
8. Lefebvre J.S. Bloom G.A., Loughead T.M. 2020. A citation network analysis of career mentoring across disciplines: a roadmap formentoring research in sport. Psychology of Sport and Exercise 49. DOI: 10.1016/j.psychsport.2020. 101676.
9. Maria S., Loureiro C. 2014. International Journal of Hospitality Management The role of the rural tourism experience economy inplace attachment and behavioral intentions. International Journal of Hospitality Management. Elsevier Ltd 40: 1-9. doi:10.1016/j.ijhm.2014.02.010.
10. Mikolov T., Sutskever I., Chen K., Corrado G.S., Dean J. 2013. Distributed representations of words and phrases and theircom-positionality Proceedings of the 26th International Conference on Neural Information Processing Systems 2 (2013): 31113119.
11. Moro S., Cortez P., Rita P. 2015. Business intelligence in banking: a literature analysis from 2002 to 2013 using text mining andlatent Dirichlet allocation. Expert Systems with Applications 42(3): 1314-1324. DOI: 10.1016/j.eswa.2014.09.024.
12. Park E., Widyanta A. 2022. Food tourism experience and changing destination foodscape: An exploratory study of an emerg-ingfood destination. Tourism Management Perspectives 42(3): 100964.
13. Pine B.J., Gilmore, J. H. 1998. The experience economy. Harvard Business Review 76(6): 97-105
14. Van der Maaten L., Hinton G. 2008. Viualizing data using t-SNE. Journal of Machine Learning Research 9: 2579-2605.
1. Cheng B., Wang M., Morch A., Chen. N, Kinshuk, Spector M. 2014. Research on e-learning in theworkplace 2000-2012: a bibliometric analysis of the literature. Educational Research Review 11: 56-72. D0I:10.1016/j.edurev.2014.01.001.
2. Chirakranont R., Sakdiyakorn M. 2022. Conceptualizing meaningful tourism experiences: Case study of a small craft beer breweryin Thailand. Journal of Destination Marketing & Management 23: 100691.
3. Claudia M., Hyungsoo T., Rauschnabel P.A. 2018. Computers in Human Behavior Determining visitor engagement throughaugmented reality at science festivals: An experience economy perspective. Computers in Human Behavior. Elsevier Ltd 82: 44-53.doi: 10.1016/j.chb.2017.12.043.
4. Devlin J. Chang M., Lee K., Toutanova K. 2018. Bert: Pre-training of deep bidirectional transformers for language under-standing.arXiv preprint: 1810.04805.
5. Hinton G.E., Roweis S.T. 2002. Stochastic Neighbor Embedding, Advances in Neural Information Processing Systems. The MITPress, Cambridge: 857-864.
6. Hwang J., Ok S. 2015. Journal of Destination Marketing & Management The antecedents and consequences of well-be-ingperception: An application of the experience economy to golf tournament tourists. Elsevier Ltd 4: 248-257. doi:10.1016/j.jdmm.2015.09.002
7. Le T., Jeong D. 2017. NLP-based approach to semantic classification of heterogeneous transportation asset data terminol-ogy.Journal of Computing in Civil Engineering 31(6): 1-13. 10.1061/(ASCE)CP. 1943-5487.00007010401 7057
8. Lefebvre J.S. Bloom G.A., Loughead T.M. 2020. A citation network analysis of career mentoring across disciplines: a roadmap formentoring research in sport. Psychology of Sport and Exercise 49. DOI: 10.1016/j .psychsport.2020. 101676.
9. Maria S., Loureiro C. 2014. International Journal of Hospitality Management The role of the rural tourism experience economy inplace attachment and behavioral intentions. International Journal of Hospitality Management. Elsevier Ltd 40: 1-9. doi:10.1016/j.ijhm.2014.02.010.
10. Mikolov T., Sutskever I., Chen K., Corrado G.S., Dean J. 2013. Distributed representations of words and phrases and theircom-positionality Proceedings of the 26th International Conference on Neural Information Processing Systems 2 (2013): 31113119.
11. Moro S., Cortez P., Rita P. 2015. Business intelligence in banking: a literature analysis from 2002 to 2013 using text mining andlatent Dirichlet allocation. Expert Systems with Applications 42(3): 1314-1324. DOI: 10.1016/j.eswa.2014.09.024.
12. Park E., Widyanta A. 2022. Food tourism experience and changing destination foodscape: An exploratory study of an emergingfood destination. Tourism Management Perspectives 42(3): 100964.
13. Pine B.J., Gilmore, J. H. 1998. The experience economy. Harvard Business Review 76(6): 97-105
14. Van der Maaten L., Hinton G. 2008. Viualizing data using t-SNE. Journal of Machine Learning Research 9: 2579-2605.
91
Фeдорова E. А.
Примeнeниe машинного обучeния и тeкстового анализа в модeлировании экономики вneчатлeний
