Application with sentiment analysis and topic modeling
•Download as PPTX, PDF•
1 like•359 views
“Peper Analysis” application makes a quick and user-friendly analysis of the neighborhoods in Sofia in the form of a heat map for tourists to find a suitable place to stay in Sofia by searching for different subjective criteria. The solution is implemented through web scraping (Selenium), sentiment analysis (TextBlob) of the acquired data, analysis (NLTK), topic modeling and word embedding (GloVe). GitHub Project: https://github.com/VIVelev/Peper-Analysis Team: Victor Velev, Vladislav Georgiev, Kaloyan Madzhunov, Martin Dacev, Peter Milev, and Telerik Arsov
Recommended
Recommended
More Related Content
More from Data Science Society
More from Data Science Society (20)
Recently uploaded
Recently uploaded (20)
Application with sentiment analysis and topic modeling
- 1. Viktor Velev, Vladislav Georgiev, Kaloyan Madjunov Martin Datsev, Petar Milev, Telerik Arsov
- 2. THE PROBLEM • The difficult tourists orientation in Sofia • The difficulty of finding a place to live
- 3. THE SOLUTION • Fast user friendly analysis of Sofia • Population density • Sport facilities • Best quarters to live in
- 4. THE TECHNOLOGIES • NLTK • NumPy • Selenium • GloVe – Stanford NLP • GenSim • Pandas • TextBlob
- 5. THE DATA ASSIMILATION • Airbnb API • Tripadvisor API • Dataset with a polyon of the quarters in Sofia
- 6. EXPLORING THE DATA • Sentiment analysis • Topic modelling • Scoring locations by topics • Categorical Search
- 9. Categorical Search - demo
- 10. Categorical Search - implementation
- 11. A HUMAN-LIKE SEARCH • Natural input • Search terms extraction • Comparing by meaning