ABOUT

Text Mining Reviews

Behind Chicken Reviews: Exploratory Analysis Through Text Mining

IID 2019-01 Social Computing 2020 Fall semester

Burgeoning amount of reviews makes review credibility questionable; we asked whether we can trust its rating or not, and analyzed the reviews texts for more objective measures.

Natural Language Processing

Delivery application reviews are burgeoning. Yet, little observation is conducted to analyze its credibility, content and trend. Using NLP and exploratory analysis, we observed the common traits of delivery app reviews and specifically those of chicken franchise brands.

Sentiment Dictionary

Observing the 'lenient' ratings of the delivery application, we sought to use topic modeling to classify the fatal words to the business and created a negative word dictionary dedicated to chickn reviews.



A delivery app review analysis project

Web crawling, text mining, natural language processing, data visualization

Natural language processing, data analysis, empirical finding

Jugyeom Kim: text mining, exploratory analysis
Soohyun Yoon: data processing
Youbeen Lee: data processing
Advisor: Dongwhan Kim

"I almost never go to a restaurant without any reviews. It's safer and more trustworthy to find a highly rated place. But often, it seems that the ratings don't always match what the place really is like..."


This study explores the texts in reviews and ratings of a delivery application and discovers ways to elevate review credibility and usefulness.

Every day 180,000 reviews are written on Tripadvisor...

Reviews are what influence us the most when it comes to decision making. However, as colossal amount of reviews are produced everyday and they are only increasing, it is getting more difficult to assess their credibility. Especially as the lengths of reviews are shortening and sheer reliance is on the rating as well, exploring the current review status of the food delivery app and opting for a more reliable way of understanding the polarity of the review is in grave need.


Preceding Studies

Reviews are vital both for the restaurant's improvement and also for objective deicision making for the consumers. However, for both parties, to glimpse through all reviews is demanding and also due to many factors, the reviews and ratings do not necessarily match as every customer has different standards and values they place the weight on. Previous attempts to empirically and objectively analyze and group the reviews are:

Data Collection and Text Mining on Chicken Reviews
Data Processing and Analysis
Trend Comparison: Google, Naver
Trend Analysis
Natural Language Processing
Influencing factors extraction
Negative Word Dictionary Generation

Methodology

We sought to first, collect food deliery app review data via web crawling. Then, we analyzed the different ratings and reviews by comparing them with those of other platforms (google, naver). Then, KoNLpy is used as the natural language processing tool, to explored the different trends in the review data. Then, to analyze if there is a trend in the text morphemes themselves, we used OKT (Open Korean Text) processor to observe such trend.

Methodology Usage
Python Selenium Web crawling of 5,000 review data/ Rating trend comparisons
KoNLPy Korean natural language processing, standardization of data
Open Korean Text Processor Observing part of speech and morpheme proportions

Results

We first observed the general rating systems and compared them with other review platforms. We then analyzed the factors involved in give the ratings. We also then analyzed the NLP results and identified unique grammatical traits in the sentences. Finally, we created a dictionary to easily identify the critical words to the business through topic modeling.

Rating System

We have analyzed our observed data "Yogi** food delivery application had a fiver-star oriented rating dispersion compared to two other reivew platforms, when comparing the five franchise chicken brands and 65 stores. Such a result signifies that the review and rating has lower credibility in Yogi**, while others have more neutral rating dispersion, it meant that the delivery app had more lenient ratings compared to their real sentiments.

Platform Number of Stores Number of Reviews Mean Rating Std. D
Yogi** 65 61,693 4.67 0.169259
Naver 64 16,407 4.32 0.187963
Google 89 1,574 3.72 0.859846

Factor Analysis

We then analyzed the inherent factors to influence its ratings and observe if there is a discrepancy between ratings and the review content. After factor analysis, it was excavated there was a positive correlation between the taste, quantity and delivery ratings, and that one is very important to one another, and that they altogether have a very strong relationship. This meant that if the delivery was late, the taste was deemed unsatisfactory.

Taste Quantity Delivery Mean Rating
Taste 1 0.713 0.568 0.883
Quantity 0.713 1 0.585 0.877
Delivery 0.568 0.585 1 0.835
Mean Rating 0.883 0.877 0.835 1

Grammatical Difference

We conducted general exploration and analysis on the grammatical parts of the sentences, and observed a speciifc trend in the moprhemes and parts of speech that comprised the negative and positive reviews. We discovered certain parts of speech and its frequency indicated negative content, and that numbers could mean severely negative reviews.


Negative Word Dictionary

Finally, based on the polarity identification, we have created a negative word dictionary of which is chicken-review specialized, under four main topics and 20 sub-topic classifications after extracting a total of 367 negative words.

Conclusion

Although we had focused primarily on one delivery app and one type of food, fried chicken (because we all love it), we analyzed if there was a discrepancy between the ratings and reviews, and it turns out many customers rate the restaurant higher than they actually think, provided their review content was analyzed. In the flood of reviews, we hoped that provide a negative word dictionary based on sentimental polarity analysis and provide indicators for both the owners and customers about the polarity of the reviews. We also identified certain parts of speech and the presence of numbers could provide negative connotations. We hope that this approach to explore the delivery review data can assist so many parties involved in the delivery app culture, that is basically bombarded every day due to its popularity.

Publication

Following article is published in the Journal of Korea Contents Association, "BEHIND CHICKEN RATINGS: An Exploratory Analysis of Yogiyo Reviews Through Text Mining" https://doi.org/10.5392/JKCA.2021.21.11. Abstract and some pages that are in English can be seen below: Please find the full paper below:


Download PDF
⇽Previous Project
Beer-food pairing