Hot Topic Prediction Scheme Using Modified TF-IDF in Social Network Environments

Noh, Yeonwoo; Lim, Jongtae; Bok, Kyoungsoo; Yoo, Jaesoo

doi:10.5626/ktcp.2017.23.4.217

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To measure the similarity between products, TF-IDF (Term Frequency -Inverse Document Frequency) algorithm is widely used (Kim and Park, 2013;Noh et al, 2017). Term frequency (TF) is a value that indicates how often a particular word appears in a document, and the higher this value, the more important it may be in a document.…”

Section: Hot Topic Detectionmentioning

confidence: 99%

“…However, cosmetics are a personal product, and the specific products that individual consumers prefer are very different. In addition, personal disposition is greatly influenced by the value of consumers' personal tastes, such as skin type and fragrance that are important to each individual (Noh et al, 2017). Unlike in the past, modern consumers are actively participating in SNS activities and evaluation activities through online site reviews.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Big Data Based Cosmetic Recommendation Algorithm

2020

JSMS

View full text Add to dashboard Cite

The purpose of this study is to develop a recommendation system to help consumers who want to purchase cosmetics to choose cosmetics more easily and comfortably. For this purpose, the cosmetics classification of 'Hwahae App', is cosmetics application in Korea, was used and developed 'recommendation system based on similarity algorithm'. This study conducted a previous study on the algorithms that make up types and recommendation systems based on Big Data. Among the numerous cosmetics, the data on consumer choice attributes and types of cosmetics were collected through the production of 'crawling Bot'. Then, the frequency of word appearance between documents was confirmed for the unstructured data information and the skin type variables of consumers. Finally we designed a system that recommends the top five products that most closely resemble the desired product, through the combination of the selection attributes that consumers want most. This study has practical value to help customers and academic meaning of recommendation system using bigdata.

show abstract

Section: Hot Topic Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Big Data Based Cosmetic Recommendation Algorithm

2020

JSMS

View full text Add to dashboard Cite

show abstract

“…To measure the similarity between products, TF-IDF (Term Frequency -Inverse Document Frequency) algorithm is widely used [3]. If past data collection studies have invested a long time to detect major hot topics, recently, it has been possible to detect information on the title, source, and contents of hot topics more easily and quickly by using crawling.…”

Section: Hot Topic Detectionmentioning

confidence: 99%

A Consumer Recommendation System based on Big Data

Yoon¹

2019

IJSBT

View full text Add to dashboard Cite

The recommendation system is a system to make consumers' choice easier by informing the result of combining information necessary for individuals in the information that consumers want in the market. Ultimately, it is a program to increase the satisfaction of consumers. In this study, consumers who choose cosmetics combine the existing attributes and extract the characteristics, and then recommend similar cosmetics, thereby enhancing the availability of consumers. For this purpose, the cosmetics classification of 'hwahae App', a representative cosmetics application in Korea, was used and 'recommendation system based on similarity algorithm' was developed.This study conducted a previous study on the algorithms that form the type and recommendation system of the recommendation system, and then developed a customized cosmetics recommendation system based on Big Data. The suggestion of such a recommended algorithm can help increase consumer satisfaction by receiving similar products that are suitable for their skin type or taste within the consumer market where there are numerous products in the market today. As a result, the company will be able to reduce the cost and time of purchasing cosmetics while increasing satisfaction by being recommended for other products with similar characteristics to existing ones. In conclusion, the application of the recommendation system using big data is meaningful in that it has not only practicality but also academic meaning by utilizing big data algorithms. 1

show abstract

Deep Learning Methods on Predicting Social Hotspots with Attention Mechanism: A Case Study on Zhihu

Xie,

Huang,

et al. 2023

2023 7th Asian Conference on Artificial Intelligence Technology (ACAIT)

View full text Add to dashboard Cite

Hot Topic Prediction Scheme Using Modified TF-IDF in Social Network Environments

Cited by 4 publications

References 0 publications

A Big Data Based Cosmetic Recommendation Algorithm

A Big Data Based Cosmetic Recommendation Algorithm

A Consumer Recommendation System based on Big Data

Deep Learning Methods on Predicting Social Hotspots with Attention Mechanism: A Case Study on Zhihu

Contact Info

Product

Resources

About