Analysis Of Community Interaction On Instagram Posts About Travel Agents In Joglosemar Area Using Social Network Analysis And Sentiment Analysis

subject Abstract

Borobudur is one of the 5 super priority destinations that aim to improve the quality and quantity of tourism destinations in Indonesia, which is expected to provide opportunities for economic growth in the surrounding region, especially Yogyakarta, Solo, and Semarang (Joglosemar). The events of 2019 showed that 4 million Borobudur tourists only stayed for 2 to 3 hours, after which they went to other places. Tour operators are one of the key aspects of the tourism supply chain, with offerings through social media platforms, especially Instagram. The purpose of the research is to find out the network structure and sentiment of community interaction shown in comments on Instagram posts about travel agents in the Joglosemar area using social network analysis and sentiment analysis methods. The research results in a network structure that is formed through identification with centrality measurement. User staycationjogja has the highest degree centrality, betweenness centrality, and eigenvector centrality values, while there are several users with the highest closeness centrality value of 1, one of which is user joglosemartour.id. The results of sentiment formed through identification with the Support Vector Machine (SVM) classification showed an accuracy level of 90%, with negative sentiment dominated by 73.1% with comments containing hashtags that do not contain useful information. Then positive sentiment by 26.9% which contains comments that are less detailed, making the percentage tend to be small. The number of true negatives (TN) is 459, false negatives (FN) are 45, true positives (TP) are 128, and false positives (FP) are 18.

Keywords: manajemen jasa, agen perjalanan, Instagram, analisis jaringan sosial, analisis sentimen

license License

Authors who publish in this journal agree to the following rules:

  1. Authors retain copyright and give the journal the right of first publication, with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors may enter separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., posting it to an institutional repository or publishing it in a book), with attribution to the journal's initial publication.
  3. Authors are permitted and recommended to post their work online (such as in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges as well as earlier and greater citation of published work.

Downloads

Download data is not yet available.