Automated Text Summarization for Indonesian Article Using Vector Space Model

Background In recent years, mail-order pharmacies have been accepted by increasingly more patients, and the prospects for mail-order pharmacies are optimistic. This article explores the patients’ satisfaction factors addressed in Business to Customer (B2C) mail-order pharmacy reviews and analyzes the sentiments expressed in the reviews. The goal of this work is to help B2C mail-order pharmacy enterprises identify patients’ concerns, continuously improve the health services level. Methods This paper was based on the Latent Dirichlet Allocation (LDA) topic model. From a B2C mail-order pharmacy of integrated e-commerce and a vertical B2C mail-order pharmacy (JD.COM and J1.COM, respectively), 136,630 pieces of over-the-counter (OTC) drug review data posted from January 1, 2015 to December 31, 2018 were selected as samples and used to explore the satisfaction factors of B2C mail-order pharmacy patients regarding the entire drug purchasing process. Then, the sentiments expressed in the drug reviews were analyzed with SnowNLP. Result Categorization of the 12 factors identified by LDA showed that 5 factors were related to logistics; these 5 factors, which also included the most drug reviews, made up 38.5% of the reviews. The number of factors related to drug prices was second, with 3 factors, and reviews of drug prices made up 25.5% of the reviews. Customer service and drug effects each had two related factors, and a smaller percentage of these reviews (13.95%) were related to drug effects. Patients still maintain positive opinions of JD.COM and J1.COM. However, some opinions on logistics and drug prices are expressed.Conclusion The most important task for mail-order pharmacies is to improve logistics. It is better to develop self-built logistics. Both types of B2C mail-order pharmacies can improve patient viscosity by implementing marketing strategies. With regard to customer service, focusing on improving employees' service attitudes is necessary.

show abstract

“…Next, the Gibbs sampling algorithm is used to estimate the posterior of the LDA model parameters [50,51,52].…”

Section: Factor Discovery Methodsmentioning

confidence: 99%

Patients' satisfaction factors mining and sentiment analysis of B2C mail-order pharmacy reviews

Liu

Zhou

Xiao-yan

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The TF-IDF (term frequency-inverse document frequency) model is first used to calculate the weight and the word frequency of each term in the document and to convert each review into a vector. Next, the Gibbs sampling algorithm is used to estimate the posterior of the LDA model parameters [50,51,52].…”

Section: Factor Discovery Methodsmentioning

confidence: 99%

Patients' satisfaction factors mining and sentiment analysis of B2C mail-order pharmacy reviews

Liu

Zhou

Xiao-yan

et al. 2019

Preprint

View full text Add to dashboard Cite

BackgroundIn recent years, mail-order pharmacies have been accepted by increasingly more patients, and the prospects for mail-order pharmacies are optimistic. This article explores the patients’ satisfaction factors addressed in Business to Customer (B2C) mail-order pharmacy reviews and analyzes the sentiments expressed in the reviews. The goal of this work is to help B2C mail-order pharmacy enterprises identify patients’ concerns, continuously improve the health services level.MethodsThis paper was based on the Latent Dirichlet Allocation (LDA) topic model. From a B2C mail-order pharmacy of integrated e-commerce and a vertical B2C mail-order pharmacy (JD.COM and J1.COM, respectively), 136,630 pieces of over-the-counter (OTC) drug review data posted from January 1, 2015 to December 31, 2018 were selected as samples and used to explore the satisfaction factors of B2C mail-order pharmacy patients regarding the entire drug purchasing process. Then, the sentiments expressed in the drug reviews were analyzed with SnowNLP.ResultCategorization of the 12 factors identified by LDA showed that 5 factors were related to logistics; these 5 factors, which also included the most drug reviews, made up 38.5% of the reviews. The number of factors related to drug prices was second, with 3 factors, and reviews of drug prices made up 25.5% of the reviews. Customer service and drug effects each had two related factors, and a smaller percentage of these reviews (13.95%) were related to drug effects. Patients still maintain positive opinions of JD.COM and J1.COM. However, some opinions on logistics and drug prices are expressed.Conclusion The most important task for mail-order pharmacies is to improve logistics. It is better to develop self-built logistics. Both types of B2C mail-order pharmacies can improve patient viscosity by implementing marketing strategies. With regard to customer service, focusing on improving employees' service attitudes is necessary.

show abstract

“…The data from social media that is the easiest to process is text. Text is the unstructured data, so that it must be conducted the pre-process until the text data ready to be processed in mining process (D S Maylawati, Sugilar, & Yudhiantara, 2018;Dian Saadillah Maylawati, Ramdhani, Rahman, & Darmalaksana, 2017;Dian Sa'Adillah Maylawati & Putri Saptawati, 2017;Slamet et al, 2018). In the requirement elicitation phase, we defined several requirements of bureaucracy sentiment analyzer application, among others: 1.…”

Section: Sentiment Analysis Architecture As Big Data Technology For Bmentioning

confidence: 99%

The Concept of Big Data in Bureaucratic Service Using Sentiment Analysis

Muliawaty

Alamsyah

Salamah

et al. 2019

International Journal of Sociotechnology and Knowledge Development

View full text Add to dashboard Cite

The implementation of bureaucratic reform in Indonesia is not optimal and faces various obstacles. At present, public services demand excellent service and meet public satisfaction. The obstacles are rigid bureaucracy, incompetent bureaucrats or apparatuses, not professional, and there are technological gaps. Rapid technological development, such as digital technology and big data, has not been responded to positively by most bureaucrats. Big Data has a great potential for improving bureaucratic and public services. With a qualitative method and a waterfall software development life cycle, this article provides the design of a bureaucracy sentiment analysis application which implements Big Data technology for analyzing the opinions about bureaucratic service in Indonesia. This is for the purpose that the bureaucratic services can be improved based on societal opinion. The results of the experiment using RapidMiner showed that sentiment analysis as a Big Data technique for bureaucratic service based on societal opinion can be used to evaluate performance better.

show abstract

Automated Text Summarization for Indonesian Article Using Vector Space Model

Cited by 47 publications

References 1 publication

Patients' satisfaction factors mining and sentiment analysis of B2C mail-order pharmacy reviews

Patients' satisfaction factors mining and sentiment analysis of B2C mail-order pharmacy reviews

Patients' satisfaction factors mining and sentiment analysis of B2C mail-order pharmacy reviews

The Concept of Big Data in Bureaucratic Service Using Sentiment Analysis

Contact Info

Product

Resources

About