Name: Aspect-Based Sentiment Analysis for Odisha's Eco-Retreat Center (en Inglés)
Price: 89640.00 CLP
Availability: InStock
Author: Panigrahi, Niranjan ; Kumar, Sudhanshu ; Parida, Pratyush
ISBN: 9786207484232

portada Aspect-Based Sentiment Analysis for Odisha's Eco-Retreat Center (en Inglés)

Formato

Libro Físico

Autor

Sudhanshu Kumar

Niranjan Panigrahi

Pratyush Parida

Editorial

LAP Lambert Academic Publishing

Idioma

Inglés

N° páginas

Encuadernación

Tapa Blanda

Dimensiones

22.9 x 15.2 x 0.3 cm

Peso

0.09 kg.

ISBN13

9786207484232

Categorías

Tecnología de la información: cuestiones generales

Aspect-Based Sentiment Analysis for Odisha's Eco-Retreat Center (en Inglés)

Sudhanshu Kumar (Autor) · Niranjan Panigrahi (Autor) · Pratyush Parida (Autor) · LAP Lambert Academic Publishing · Tapa Blanda

Libro Nuevo

$ 89.640

$ 124.500

Ahorras: $ 34.860

28% descuento

Envío normal

Origen: Estados Unidos (Costos de importación incluídos en el precio)

Se enviará desde nuestra bodega entre el Lunes 15 de Julio y el Lunes 22 de Julio.

Lo recibirás en cualquier lugar de Chile entre 1 y 3 días hábiles luego del envío.

Reseña del libro "Aspect-Based Sentiment Analysis for Odisha's Eco-Retreat Center (en Inglés)"

In the sustainable global goals, economic growth is one of the major challenges faced by any part of the world. Odisha, one of the developing eastern state of India, has many well-known tourist places which can contribute to revenue generation and economic growth. Recently, its government has planned to make some tourist places as "eco-retreat centers" which can attract more tourist to these places. To achieve this objective, the tourist feedback must be analyzed thoroughly which will enhance both quality of service and growth in tourism sector. In this context, an aspect-based sentiment analysis framework is proposed based on Google map reviews given by tourists on Konark tourist spot. Initially, the online reviews are scrapped using Selenium. Then a transfer learning method is proposed utilizing and fine tuning BERT model. The performance is compared with other state-of-the-art models. Further, to enhance the reviews scrapping speed, an Incremental Review Aggregator (IRA) algorithm is proposed. Prompt engineering and few-shot learning with GPT3 is also proposed for better understanding of the aspects. Finally, a web-based application is developed to automate the tasks.