Extracting Advertising Elements and the Voice of Customers in Online Game Reviews

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The manuscript addresses a timely and relevant research question. However, there are some points to be considered before the paper can be considered for publication;

• The authors should add a paragraph discussing recent advances in transformer-based sentiment analysis and why classical ML methods were preferred.
• The paper uses traditional metrics (OA, F1, NA, PA) but omits AUC-ROC, which is important for imbalanced data.
• Topic naming relies on subjective interpretation by three experts, but the methodology for mapping words to advertising elements lacks transparency. The authors could include a brief explanation or table on inter-rater reliability (e.g., Cohen’s Kappa) or expert consistency in labeling.
• The dataset is limited to Steam's “early access” games. This may bias results toward positively skewed promotional content. The paper should acknowledge this limitation more explicitly and recommend validating the method on broader datasets (e.g., mobile app stores, Metacritic).

Comments on the Quality of English Language

A professional language edit is recommended to improve readability.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Dear authors,

Thank you for the opportunity to review the manuscript entitled “Extracting Advertising Elements and the Voice of Customers in Online Game Reviews”. The topic is timely and relevant to key stakeholders such as the scientific community, the gaming platforms and those who play. The real-time user comments analysis from the Steam platform is interesting. Moreover, the authors have used relevant research methods such as Natural Language Processing, Support Vector Machine, Decision Tree and Naïve Bayes. We would appreciate it if the authors could minor revise their manuscript to address the following issues:

• A more extensive presentation of the main results obtained so far in the field of online game review analysis. The authors presented in the introduction (lines 71-77) the current state of the knowledge, but I believe there is room for an extensive review of prior studies
• Literature review – While literature is comprehensive, theoretical integration remains somehow limited. I think it would be suitable to present the main consumer behavior theories that you used.
• Methodology (Data collection) - I think it would be useful to mention the period in which the analyzed reviews were written.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf