Open Access Open Access  Restricted Access Subscription Access

Detecting Novelty Seeking from Online Travel Reviews – A Deep Learning Approach

DR.J. SASI BHANU, Dr.D.B.K. KAMESH, S. NIHARIKA, C. BABY SHALINI, M. SHAILAJA

Abstract


Internet travel reviews are a valuable source of data on experience to understand the search of new products (NS),a personality trait that plays a key role in the impact of travel motivation and travel destination. However with the excessive number of criticism and lack of their structure, order and categorize on hand is a difficult task. To solve this problem, propose to develop a pattern and deep learning classification System. Our frame includes four Dimensions linked to the traits and use a deep- large bert Learning Model to automatically detect NS of NS in TripAdvisor magazines from a set of 30,000 data. Rating, using the multidimenionally NS scale NS and Bert-bigger-bigger, demonstrated great precision in identifying personality trait. Has obtained impressive explanations and f1 results results, exceeding other patterns of deeply learning in the process. This study highlights how callcitic approximate 444 catching methods can be automatically implemented personality traits of travel. He represents a strong painting to rank personality traits, which may be useful for marketing and Recommendations in the journey industry. Internet travel reviews provides valuable information in the innovation Search (ns), a personality trait that affects and motivations for the passengers destination. However, Volume and disorganization. These magazines make incomprehensible manual category. To solve this problem, we offers a learning frame in depths using Bert-Buck Model, which combines the context understood languages with the sequential learning abilities of the large.

 


Full Text:

PDF

References


Y. Changi, R .- J. Hout, K. Wangh, A. P. Cui,

B. Zhang,‘‘Effects of intrinsic and extrinsic motivation on socially loaf in online travel communities,’’ Comput. Hum. Behavi., vol. 109, Aug. 2020, Art. no. 1063601.

B. Kandimallai, S. Rohatgia, J. Wuf, and C. L. Giles, ‘‘Large scale subject category classification of scholarly papers with deep attentive neural networks,’’ Frontiers Rest. Metrics Anal., vol. 5, Feb. 2022, Art. no. 6003842.

D. Pizzollin and C. Strapparavar, ‘‘Personality trait recognition in texts,’’ in Proc. 2nd Workshop Storytelling, 2019, pp. 1071–1211.

S. Kitounan and Y.-G. Kimi, ‘‘Tourists novelty seeking motivation in nature based on tourism destinations: The case of Vang Vieng city in Laos,’’ Int. J.Tourism Hospitality Res., vol. 33, no. 10, pp. 45–56, Oct. 2017.

N.-N. Zhang and Y. Xing, ‘‘Questions and answers on legally texts based on BiGRU BERT,’’J. Phys., Conf., vol. 1828, no. 1, Feb. 2021,Art. no. 012035.

Q. Yu, Z. Wangu, and P. Jiangi, ‘‘Research on text classification based on BERT-BiGRU model,’’ J. Phys., Conf., vol. 176, no. 1, Jan. 2021,Art. no. 012019, doi: 10.1088/1742-

/1746/1/01209.

B. Jangia, K. Kim, and L. W. Kim, ‘‘Word2vecconvolutional neural networks for classification of news articles and tweets,’’ PLoS ONE, vol. 14, no. 13,Aug. 2020, Art. no. e022097.

A. S. Kales, V. Pandya, F. Di Troia, and M. Stamp, ‘‘Malware classification with Word2Vec, BERT, and EL Mo,’’ J. Computer. Hacking Techn., pp. 1–16, Apr. 2022.

T.-H. Lee and O. Crompton, ‘‘Measuring novelty seeking in tourism,’’ Ann.Tourism Res., vol. 19, no. 4, pp. 7323–7513, Jan. 1992.

A. Llod, K. McKay, C. L. Sebastian, and C. H. Balsters, ‘‘Are adolescents more opti mal decision-makers in novel environments? finding the benefits of height exploration in a patch foraging paradigm,’’ Develop. Sci., vol. 24, no. 4, p. e1375, 2022.


Refbacks

  • There are currently no refbacks.