Algorithm for extracting product feature from e-commerce comment

Kaewphet, Chanida; Wisitpongpun, Nawaporn

doi:10.11591/ijeecs.v22.i2.pp1199-1207

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Building a good image of a brand can be done by taking advantage of the transparency of social media data, for example by displaying honest responses from customers [13]. But, fully reading reviews is quite difficult [34]. To increase popularity, a social media is needed, but high popularity must be in line with good operational performance [35].…”

Section: Methodsmentioning

confidence: 99%

The implementation of social customer relationship management for tourism information system

Ibrahim

Indah²,

Meytri³

2021

IJEECS

View full text Add to dashboard Cite

Semambu island village, Ogan Ilir regency, south Sumatra has been used as an agricultural and livestock education tour destination since November 2017 and there has been no customer data management since then. The use of social media as a promotional tool has not been done to its maximum potential. This can be seen from 189 people who liked its Facebook page or 11.05% out of the reached users, 192 followers or 11.23% and those who interacted as many as 114 people or 6.67% from the total users. Meanwhile, there were 709 followers on its Instagram which consisted of 48% men and 52% women at the time of the study. This research applied social customer relationship management (social CRM) in a website-based system. The waterfall model development method supported the customer relations management by utilizing Facebook and Instagram to improve customer relationships in providing travel information, knowing interest and listening to complains as well as their suggestions based on interactions with the social media users as existing and prospective customers.

show abstract

Section: Methodsmentioning

confidence: 99%

The implementation of social customer relationship management for tourism information system

Ibrahim

Indah²,

Meytri³

2021

IJEECS

View full text Add to dashboard Cite

show abstract

“…[18], and iii) stemming word, the process of substituting words that have the same meaning or words with the same root with only one word. This reduces the number of redundant words in the document and help increase the efficiency of document classification [19]- [21]. Figure 2 shows the data preparation process which consists of 3 steps: i) word segmentation, the process of word cutting by comparing with words archived in a dictionary, ii) stop word removal, the process of removing words that are not important from the document by comparing it to the stop words stored on the database, and iii) word stemming, the process of replacing words with the same meaning or words with the same root with a certain word by comparing with the database.…”

Section: Data Preprocessingmentioning

confidence: 99%

Classifying thai news headlines using an artificial neural network

Chanakot

Sanrach²

2023

Bulletin EEI

View full text Add to dashboard Cite

This research aimed to measure the effectiveness of Thai news headlines classification using an artificial neural network (ANN). The headlines consisted of i) political news, ii) sports news, iii) economic news, and iv) crime news, 1,200 headlines in total. The distribution of headlines was measured by using chi-square, information gain, and term frequency inverse class frequency (TFICF). Threshold default value was set in relation to terms of headlines before cross-validation was employed to categorize the data to examine the efficiency of the model using a neural network algorithm in classifying the headlines. The investigation of the news headline classification efficiency revealed that the 15-fold data division using TFICF was the most accurate in classifying headlines, with the accuracy rate of 99.60% and F-measure rate of 99.05%. Moreover, it was found that when more news headlines were provided as the learning data, the news headline classification became more accurate. Likewise, appropriate threshold value determination facilitated the selection of appropriate features in the headlines and resulted in more effective and accurate classification. Hence, it can be concluded that headline classification will be more accurate if the appropriate amount of learning data exists, and appropriate threshold value was set.

show abstract

“…Deep neural networks have transformed plant pathology by producing remarkable outcomes without the requirement for time-consuming feature engineering [8]. Deep neural networks have improved picture categorization accuracy dramatically.This offers researchers use of different techniques to identify diseases in plants.…”

Section: International Journal On Recent and Innovation Trends In Com...mentioning

confidence: 99%

Implementation of Deep CNN Model for the Detection of Plant Leaf Disease

Deepa,

Vijayanand,

Danesh

et al. 2023

IJRITCC

View full text Add to dashboard Cite

The potato is the most important tuber crop in the world, and it is grown in about 125 different nations. Potato is the crop that is most commonly consumed by a billion people worldwide, virtually every day, behind rice and wheat. However, a number of bacterial and fungal diseases are causing the potato crop's quality and yield to decline. Potato Leaf diseases must be promptly identified and prevented to increase production. Various researchers look for solutions to protect plants instead of traditional processes which take more time. Recent technological developments have thrown up many alternates to traditional methods which are labour intensive. The application of AlexNet model Deep Convolutional Neural Network(CNN) to recognise diseases in potato plants avoids the disadvantages of selecting disease spot features artificially and makes more objective the plant disease feature extraction. It improves research efficiency and speeds up technology transformation. Accuracies ranging from 85% - to 95% were obtained using AlexNet model Deep.

show abstract

Algorithm for extracting product feature from e-commerce comment

Cited by 3 publications

References 13 publications

The implementation of social customer relationship management for tourism information system

The implementation of social customer relationship management for tourism information system

Classifying thai news headlines using an artificial neural network

Implementation of Deep CNN Model for the Detection of Plant Leaf Disease

Contact Info

Product

Resources

About