Department of Economics and Business Economics

Why do Internet consumers block ads? New evidence from consumer opinion mining and sentiment analysis

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Purpose: The number of Internet consumers who adopt ad-blocking is increasing rapidly all over the world. The purpose of the paper is to evaluate this phenomenon by: (1) assembling the existing considerations and key theoretical aspects of the determinants of online ad-blocking; and (2) by exploring the consumers’ beliefs and sentiments towards online ads and expected outcomes of ad-blocking behavior.

Methodology: Data consist of 4,093 consumers’ opinions in response to the news items about ad-blocking, published by a leading news and technology website in the period 2010-2016. The unstructured data is analyzed using probabilistic topic modeling and sentiment analysis.

Findings: Five main topics are identified, unveiling the hidden structure of consumers’ beliefs. A sentiment analysis profiling the clustered opinions reveals that the opinions that are focused on the behavioral characteristics of ads express the strongest negative sentiment, while the opinions centered on the possibility to subscribe to an ad-free fee-financed website are characterized on average by a positive sentiment.

Practical implications: The findings provide useful insights for practitioners to create/adopt more acceptable ads that translate into less ad-blocking and improved Internet surfing experience. It brings insights on the question of whether ad-free subscription websites have or do not have the potential to become a viable business opportunity.

Originality: The research (1) improves the current understanding of the determinants of ad-blocking by introducing a conceptual framework and testing it empirically; (2) makes use of consumer-generated data on the Internet; and (3) implements novel techniques from the data mining literature.
Original languageEnglish
JournalInternet Research
Volume29
Issue1
Pages (from-to)144-166
ISSN1066-2243
DOIs
Publication statusPublished - 2019

    Research areas

  • ads, ad-blocking, consumer, topic modeling, sentiment analysis, text-mining

See relations at Aarhus University Citationformats

ID: 126221073