The 1st International Conference on Computer Science and Engineering Technology Universitas Muria Kudus

Research Article

Sentiment Analysis Towards Courier Service: Case Study on JNE Semarang

Download1129 downloads
  • @INPROCEEDINGS{10.4108/eai.24-10-2018.2280499,
        author={Erika Devi Udayanti and Aulia Arif Rahman and Etika Kartikadharma},
        title={Sentiment Analysis Towards Courier Service: Case Study on JNE Semarang},
        proceedings={The 1st International Conference on Computer Science and Engineering Technology Universitas Muria Kudus},
        publisher={EAI},
        proceedings_a={ICCSET},
        year={2018},
        month={11},
        keywords={sentiment analysis jne classification k-nn},
        doi={10.4108/eai.24-10-2018.2280499}
    }
    
  • Erika Devi Udayanti
    Aulia Arif Rahman
    Etika Kartikadharma
    Year: 2018
    Sentiment Analysis Towards Courier Service: Case Study on JNE Semarang
    ICCSET
    EAI
    DOI: 10.4108/eai.24-10-2018.2280499
Erika Devi Udayanti1,*, Aulia Arif Rahman1, Etika Kartikadharma1
  • 1: Universitas Dian Nuswantoro
*Contact email: erikadevi@dsn.gmail.com

Abstract

Society as customers often gives an opinion about the company's product and service. Opinion delivered by customers can be both in positive and negative judgments. It is in the form of opinions that describe a customer's emotional expression. Therefore, it is important for companies to be able to understand customers' emotional tendencies from the opinions of texts submitted online. In this study, data text is used in the form of opinions of users of JNE Semarang courier services to conduct sentiment analysis by mining opinions from customer reviews. This research generally proposes the implementation of sentiment analysis of JNE customer's opinion by using K-nearest Neighbor algorithm to classify customer's opinion regarding JNE services. The Confusion Matrix model is adapted to measure the accuracy of the classification results. And the results show that majority opinions classify into negative sentiment with the highest accuracy on value k=7