Aspect based Sentiment Oriented Summarization of Hotel Reviews

Nadeem Akhtar, Nashez Zubair, Kumar Abhishek, Tameem Ahmad

Procedia Computer Science · 2017 · 119 citations · 11 references

DOIFull text

Open access

Concepts

TL;DR

Hotel booking sites rely on ratings and reviews, yet most travelers lack time to read all reviews, limiting insight. The study examines hotel reviews to uncover insights that ratings alone miss. The authors crawled reviews and metadata, classified them by common aspects, applied LDA topic modeling to reveal hidden aspects, and performed sentiment analysis and summarization. The results lay groundwork for a hotel recommender system, with future work outlined.

Abstract

Hotel booking websites use online ratings and customer feedback to help the customer's decision making process but reviews provide a better insight about the hotel but most travellers don't have the time or patience to read all reviews. This study analyzes the hotel reviews and gives information that ratings might overlook. The reviews and metadata are crawled from website and classified into predefined classes as per some of the common aspects. Then Topic modelling technique (LDA) is applied to identify hidden information and aspects, followed by sentiment analysis on classified sentences and summarization. Finally we discuss results and future work, ultimately building towards Hotel Recommender System.

References

11