Scene Classification, Data Cleaning, and Comment Summarization for Large-Scale Location Databases

Hsu Yung Cheng, Chih Chang Yu

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


This paper presents a framework that can automatically analyze the images and comments in user-uploaded location databases. The proposed framework integrates image processing and natural language processing techniques to perform scene classification, data cleaning, and comment summarization so that the cluttered information in user-uploaded databases can be presented in an organized way to users. For scene classification, RGB image features, segmentation features, and the features of discriminative objects are fused with an attention module to improve classification accuracy. For data cleaning, incorrect images are detected using a multilevel feature extractor and a multiresolution distance calculation scheme. Finally, a comment summarization scheme is proposed to overcome the problems of unstructured sentences and the improper usage of punctuation marks, which are commonly found in customer reviews. To validate the proposed framework, a system that can classify and organize scenes and comments for hotels is implemented and evalu-ated. Comparisons with existing related studies are also performed. The experimental results validate the effectiveness and superiority of the proposed framework.

Original languageEnglish
Article number1947
JournalElectronics (Switzerland)
Issue number13
StatePublished - 1 Jul 2022


  • deep learning
  • image analysis
  • image classification
  • natural language processing


Dive into the research topics of 'Scene Classification, Data Cleaning, and Comment Summarization for Large-Scale Location Databases'. Together they form a unique fingerprint.

Cite this