Search results

This paper aims to explore textual patterns in ten years of electronic word-of-mouth communications amongst social media (SM) users of the Java Jazz Festival.

This study uses a data-scraping technique to gather user-generated content from Twitter. Word-cloud and word-frequency analysis, along with descriptive coding and pattern matching, are used to categorise the initial findings. Trends and differences in terms of the number of tweets over a ten-year period were examined using analysis of variance and seasonality analysis.

From more than 1.3 million Twitter tweets between 2008 and 2018, this study identified six initial themes. Quantitative analysis revealed that the number of tweets differed significantly in the four quarters of the ten-year period.

The results of this study contrast with the claim that digital media communication generally occurs before a festival begins and are least during the festival. Nevertheless, this study supports the notion that SM interaction results in positive consequences, drives conversations amongst users and increases engagement.

This study offers five practical implications for music festival organisers and related entities.

To the best of the author’s knowledge, this study is the first to provide a systematic and practical data mining and interpretation approach from Twitter within a ten-year period in the Asia Pacific context, through the case of the Java Jazz Festival.

研究目的 – 本论文旨在分析十年来Java爵士音乐节的社交媒体用户发布的文字模式，从而探索其网络口碑效应。

本论文使用网络爬虫技术，从Titter上面搜集用户产生的文本数据。本论文采用文字云和词频分析法，以及描述性编码和模型匹配等方式，来对初步结果进行归类。本论文使用ANOVA和季节性分析的方法对tweets十年中的变化和趋势进行分析检验。

本论文通过对在2008年至2018年的超过130万tweets进行分析，初步指出了六大主题。定量分析结果表明十年内四个季节中的tweets数量相差甚大。

本论文结果总体上与传统上认为的电子媒体沟通发生在节庆之前或者至少在节庆发生中的论断相左。本论文结果支持论断：社交媒体互动产生积极的影响，带动用户之间的对话，以及参与度。

本论文是首篇文章，以Java爵士音乐节为例，针对亚太地区十年间Twitter数据进行系统和实际数据挖掘和解读。