| Autor: |
Kaur, Chamandeep, Deshmukh, Araddhana Manisha Arvind, Begum, Ahmed Unnisa, M. J., Kurian, Duraisamy, Suganthi, Malpani, Ajay |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
International Journal of Intelligent Systems and Applications in Engineering; Vol. 11 No. 7s (2023): Advancements in Machine Learning for Computer Science and Decision Support Systems; 708-717 |
| ISSN: |
2147-6799 |
| Popis: |
Understanding the qualities of visitor traffic is crucial for travel behavior specialists because the traits impact how executives in the tourist business utilize techniques of fascination seeking to promote commercial goods. Nonetheless, the vast majority of the travel industry research techniques are not either versatile or cost-proficient to find fundamental development designs due to the enormous datasets. With propels in data and correspondence innovation, online media stages give enormous informational collections produced by a huge number of individuals from various nations, which can all be gathered expense effectively. To overcome all the existing drawbacks, A graph-based technique for detecting visitor movement patterns from Twitter data is provided in this paper. To begin, the tweets with geotags that have been gathered are filtered to exclude those that were not sent by visitors. Instant generates the tourist graph by finding nodes and edges using the median support value-based graph algorithm (MSBG). Using the sigmoid-based Markov clustering algorithm (SMCL), The network analysis algorithms are then utilized to predict tourist patterns of movement, such as the most prominent tourist attractions, focus attractions, and tour itineraries. The experimental results in terms of the proposed work provide a better outcome in correlation with the current techniques. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
