Publications
2022
Poecze, Flora; Ebster, Claus; Strauss, Christine
In: Personal and Ubiquitous Computing, Bd. 26, Nr. 3, S. 901–910, 2022, ISSN: 1617-4909.
Abstract | Links | BibTeX | Schlagwörter: ANTECEDENTS, MOTIVATIONS, Online gaming, Self-marketing, Sentiment analysis, Social media metrics, TWITTER
@article{ea91d596e44d40998eb2bde3bc6a54b6,
title = {Let’s play on Facebook: using sentiment analysis and social media metrics to measure the success of YouTube gamers’ post types},
author = {Flora Poecze and Claus Ebster and Christine Strauss},
doi = {10.1007/s00779-019-01361-7},
issn = {1617-4909},
year = {2022},
date = {2022-06-01},
journal = {Personal and Ubiquitous Computing},
volume = {26},
number = {3},
pages = {901–910},
publisher = {Springer-Nature},
abstract = {This paper discusses the analysis results of successful self-marketing techniques on Facebook pages in the cases of three YouTube gamers: PewDiePie, Markiplier, and Kwebbelkop. The research focus was to identify significant differences in terms of the gamers' user-generated Facebook metrics and commentary sentiments. Analysis of variance (ANOVA) and k-nearest neighbor sentiment analysis were employed as core research methods. ANOVA of the classified post categories revealed that photos tended to show significantly more user-generated interactions than other post types, while, on the other hand, re-posted YouTube videos gained significantly fewer numbers in the retrieved metrics than other content types. K-nearest neighbor sentiment analysis pointed out underlying follower negativity in cases where user-generated activity was relatively low, thereby improving the understanding of the opinion of the masses previously hidden behind metrics such as the number of likes, comments, and shares. The paper at hand highlights the methodological design of the study as well as a detailed discussion of key findings and their implications, and future work. The results per se indicate the need to utilize natural language processing techniques to optimize brand communication on social media and highlight the importance of considering machine learning sentiment analysis techniques for a better understanding of consumer feedback.},
keywords = {ANTECEDENTS, MOTIVATIONS, Online gaming, Self-marketing, Sentiment analysis, Social media metrics, TWITTER},
pubstate = {published},
tppubtype = {article}
}
This paper discusses the analysis results of successful self-marketing techniques on Facebook pages in the cases of three YouTube gamers: PewDiePie, Markiplier, and Kwebbelkop. The research focus was to identify significant differences in terms of the gamers' user-generated Facebook metrics and commentary sentiments. Analysis of variance (ANOVA) and k-nearest neighbor sentiment analysis were employed as core research methods. ANOVA of the classified post categories revealed that photos tended to show significantly more user-generated interactions than other post types, while, on the other hand, re-posted YouTube videos gained significantly fewer numbers in the retrieved metrics than other content types. K-nearest neighbor sentiment analysis pointed out underlying follower negativity in cases where user-generated activity was relatively low, thereby improving the understanding of the opinion of the masses previously hidden behind metrics such as the number of likes, comments, and shares. The paper at hand highlights the methodological design of the study as well as a detailed discussion of key findings and their implications, and future work. The results per se indicate the need to utilize natural language processing techniques to optimize brand communication on social media and highlight the importance of considering machine learning sentiment analysis techniques for a better understanding of consumer feedback.
2018
Poecze, Flora; Ebster, Claus; Strauss, Christine
Social media metrics and sentiment analysis to evaluate the effectiveness of social media posts Artikel
In: Procedia Computer Science, Bd. 130, S. 660–666, 2018, ISSN: 1877-0509.
Abstract | Links | BibTeX | Schlagwörter: HBE, Self-marketing, Sentiment analysis, Social media metrics
@article{645f759338fc4f87baae686836f48ed8,
title = {Social media metrics and sentiment analysis to evaluate the effectiveness of social media posts},
author = {Flora Poecze and Claus Ebster and Christine Strauss},
doi = {10.1016/j.procs.2018.04.117},
issn = {1877-0509},
year = {2018},
date = {2018-04-24},
journal = {Procedia Computer Science},
volume = {130},
pages = {660--666},
publisher = {Elsevier},
abstract = {The present paper presents the results of an analysis of indicators underlying successful self-marketing techniques on social media. The participants included YouTube gamers. We focus on the content of their communication on Facebook to identify significant differences in terms of their user-generated Facebook metrics and commentary sentiments. Methodologically, ANOVA and sentiment analysis were applied. ANOVA of the classified post categories revealed that re-posted YouTube videos gained significantly fewer likes, comments, and shares from the audience. On the other hand, photos tended to show significantly more follower-generated actions compared to other post types in the sample. Sentiment analysis revealed underlying follower negativity when user-generated activity tended to be relatively low, offering valuable complementary results to the mere analysis of other post indicators, such as the number of likes, comments, and shares. The results indicated the necessity to utilize natural language processing techniques to optimize brand communication on social media and highlighted the importance of considering the opinion of the masses for better understanding of consumer feedback.},
keywords = {HBE, Self-marketing, Sentiment analysis, Social media metrics},
pubstate = {published},
tppubtype = {article}
}
The present paper presents the results of an analysis of indicators underlying successful self-marketing techniques on social media. The participants included YouTube gamers. We focus on the content of their communication on Facebook to identify significant differences in terms of their user-generated Facebook metrics and commentary sentiments. Methodologically, ANOVA and sentiment analysis were applied. ANOVA of the classified post categories revealed that re-posted YouTube videos gained significantly fewer likes, comments, and shares from the audience. On the other hand, photos tended to show significantly more follower-generated actions compared to other post types in the sample. Sentiment analysis revealed underlying follower negativity when user-generated activity tended to be relatively low, offering valuable complementary results to the mere analysis of other post indicators, such as the number of likes, comments, and shares. The results indicated the necessity to utilize natural language processing techniques to optimize brand communication on social media and highlighted the importance of considering the opinion of the masses for better understanding of consumer feedback.