Unlock instant, AI-driven research and patent intelligence for your innovation.

Sentiment Classification Method for Tourism Evaluation Combining at_gru Neural Network and Sentiment Dictionary

A sentiment dictionary and neural network technology, applied in the field of natural language processing and deep learning, can solve problems such as inability to extract features well, inaccurate classification, etc., to achieve the effect of increasing classification accuracy

Active Publication Date: 2022-03-29
SHANGHAI UNIVERSITY OF ELECTRIC POWER
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A large number of scholars at home and abroad have done related research. He Youshi proposed multi-feature combination semantic mining based on decision trees. Xia Mingshou and others used ICTCLAS word segmentation technology and word frequency statistics to mine product evaluation features, but failed to use deep learning. Therefore, more accurate features cannot be extracted well. Li Jie and others used the CNN model for short text analysis, but failed to make full use of contextual semantic information, resulting in inaccurate classification problems.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sentiment Classification Method for Tourism Evaluation Combining at_gru Neural Network and Sentiment Dictionary
  • Sentiment Classification Method for Tourism Evaluation Combining at_gru Neural Network and Sentiment Dictionary
  • Sentiment Classification Method for Tourism Evaluation Combining at_gru Neural Network and Sentiment Dictionary

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0048] Regarding the following tourism comment text, "It is worthy of being one of the four major gardens in China! No matter in scale or setting, it all reflects the unique small bridges and flowing water houses in the south of the Yangtze River. The pavilions are so beautiful, and the winding paths lead to secluded stone paths! The lotus pond in the water ...". Implement the following steps:

[0049] 1. Data preprocessing

[0050] 1) Perform word segmentation, noise removal and other processing on the data, and finally produce the following results:

[0051] "Worthy of the four major gardens in China! Regardless of the scale and setting, none of them reflect the unique small bridges and flowing water in the south of the Yangtze River, the beautiful pavilions, winding paths leading to secluded stone paths! A few days..."

[0052] 2) Perform word vector training for each word to generate a 50-dimensional word vector, as follows:

[0053] "garden 0.15164 0.30177 -0.16763 0....

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention relates to a kind of travel evaluation emotion classification method that combines At_GRU neural network and emotion dictionary, in order to realize the evaluation semantic classification of tourism users to the whole travel according to the evaluation text of the whole journey by tourists, comprising the following steps: 1) Emotional feature processing Stage: Vectorize the emotional features in travel reviews by constructing a composite tourism-specific sentiment dictionary; 2) Data preprocessing stage: Train word vectors for the original review text and splicing context vectors, and combine the spliced ​​vectors with vectorized 3) Bidirectional GRU text semantic classification model stage: train the bidirectional GRU neural network and classify the sentiment of tourism evaluation. Compared with the prior art, the invention has the advantages of high precision, considering the accuracy of emotion dictionary and the robustness of machine learning.

Description

technical field [0001] The invention relates to the fields of natural language processing and deep learning, in particular to a method for classification of tourism evaluation emotions combined with At_GRU neural network and emotion dictionary. Background technique [0002] Tourist itinerary evaluation is to record tourists’ feedback on a specific itinerary formulated by a certain scenic spot on a travel website. It is the most direct expression of tourists’ satisfaction or suggestions for this itinerary, and is the link between tourists and tourism websites vertically. Through the evaluation of travel routes, passengers can elaborate on the itinerary, accommodation, transportation arrangements, etc. of the route for other passengers to learn from. Travel companies can also listen to opinions directly, quickly respond to improvements, adjust the details of the travel route, improve services, strengthen passenger satisfaction. Therefore, quickly and accurately analyzing and ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/35G06N3/02
CPCG06N3/02
Inventor 曹渝昆巢俊乙
Owner SHANGHAI UNIVERSITY OF ELECTRIC POWER