Articolul precedent |
Articolul urmator |
![]() |
![]() ![]() |
Ultima descărcare din IBN: 2024-01-31 10:45 |
![]() POPESCU, Alexandru, RUSU, Alexandru, GROZA, Octavian. Preliminary results of Big Data analysis for Iași, Romania. In: Sisteme Informaționale Geografice: In memoriam Prof. Univ. Emerit. dr. Ioan DONISĂ, Ed. 29, 30 martie 2023, Iași. Iași : GIS and Remote Sensing, 2023, Ediția 29, p. 5. |
EXPORT metadate: Google Scholar Crossref CERIF DataCite Dublin Core |
Sisteme Informaționale Geografice Ediția 29, 2023 |
||||||
Simpozionul "Sisteme Informaționale Geografice" 29, Iași, Romania, 30 martie 2023 | ||||||
|
||||||
Pag. 5-5 | ||||||
|
||||||
![]() |
||||||
Rezumat | ||||||
The city of Iasi is one of the most visited cities in Romania, known for its rich cultural heritage and historical landmarks. In this context, analyzing big data from reviews of the main tourist attractions and the transportation system can provide valuable insights to stakeholders such as the local government, tour operators, and transport companies. The first step in the analysis is data collection. Reviews from various online platforms such as Google Reviews or blogs are gathered and preprocessed for further analysis. This includes data cleaning, removal of irrelevant data, and categorization of reviews into different segments based on the type of attraction or transportation system. Once the data is collected, the analysis begins with exploratory data analysis to gain insights into the reviews' overall sentiment, distribution, and frequency. This is followed by text mining techniques such as sentiment analysis, topic modeling, and clustering to extract valuable information from the reviews. The sentiment analysis can help understand the visitors' overall sentiment towards the main attractions and transportation system in the city. This includes identifying the positive and negative aspects of each attraction and transportation mode. The results can be used to improve the visitor experience by focusing on the areas with negative sentiment. Topic modeling can help identify the most frequent topics discussed in the reviews, such as the quality of service, accessibility, and cleanliness. The topics can be used to identify areas that need improvement or highlight the strengths of the city's main attractions and transportation system. Clustering techniques can group reviews based on their similarity, allowing the stakeholders to identify patterns in the data that can help improve the tourist experience in the city. For example, reviews related to accessibility can be clustered together, and recommendations can be made to improve accessibility for tourists. The analysis can also be extended to identify trends over time. By collecting and analyzing data over a period, stakeholders can identify seasonal variations, changes in tourist preferences, and evaluate the effectiveness of previous improvements. |
||||||
|