Sirvi Autor "Berik, Anton" järgi

Tulemuste filtreerimiseks trükkige paar esimest tähte
Nüüd näidatakse 1 - 1 1
  • Pisipilt
    listelement.badge.dso-type Kirje ,
    AI-Powered Food Safari: Restaurant Picks for the Modern Traveller
    (Tartu Ülikool, 2025) Berik, Anton; Banerjee, Somnath, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Arvutiteaduse instituut
    This thesis presents a system for AI-powered restaurant recommendation based on user preferences, customer reviews, and metadata. The approach leverages natural language processing techniques, in particular, aspect-based sentiment analysis and Large Language Model evaluate restaurants on a wide range of factors, such as food quality, service, and atmosphere. By interpreting user prompts, the system adjusts the importance of different aspects and uses sentiment scores from reviews alongside restaurant metadata like location and ratings to calculate a final ranking. The system supports multilingual inputs and includes steps for data collection, cleaning, and structured analysis. The result is a personalized and flexible recommendation engine that provides users with relevant and context-aware restaurant suggestions.