CoChat
Sign Up
Cited by 1,069Digital Marketing and Social MediaMarketing and Advertising StrategiesConsumer Market Behavior and Pricing

Advertising Content and Consumer Engagement on Social Media: Evidence from Facebook

Open access
Lee, Dokyun, Hosanagar, Kartik, Nair, Harikesh S.·2018·Management Science
DOI 10.1287/mnsc.2017.2902
Open this paper in CoChat — free account

Abstract

We describe the effect of social media advertising content on customer engagement using data from Facebook. We content-code 106,316 Facebook messages across 782 companies, using a combination of Amazon Mechanical Turk and natural language processing algorithms. We use this data set to study the association of various kinds of social media marketing content with user engagement—defined as Likes, comments, shares, and click-throughs—with the messages. We find that inclusion of widely used content related to brand personality—like humor and emotion—is associated with higher levels of consumer engagement (Likes, comments, shares) with a message. We find that directly informative content—like mentions of price and deals—is associated with lower levels of engagement when included in messages in isolation, but higher engagement levels when provided in combination with brand personality–related attributes. Also, certain directly informative content, such as deals and promotions, drive consumers’ path to conversion (click-throughs). These results persist after incorporating corrections for the nonrandom targeting of Facebook’s EdgeRank (News Feed) algorithm and so reflect more closely user reaction to content than Facebook’s behavioral targeting. Our results suggest that there are benefits to content engineering that combines informative characteristics that help in obtaining immediate leads (via improved click-throughs) with brand personality–related content that helps in maintaining future reach and branding on the social media site (via improved engagement). These results inform content design strategies. Separately, the methodology we apply to content-code text is useful for future studies utilizing unstructured data such as advertising content or product reviews. The online appendix is available at https://doi.org/10.1287/mnsc.2017.2902 . This paper was accepted by Chris Forman, information systems.

Integrity signals

Registry

Crossref · 10.1287/mnsc.2017.2902

Cites

85 of 85 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The algorithms monitor the amount of time particular kinds of content keep the particular user engaged and use that data to continuously adjust the content so that the user remains engaged for ever lengthening periods.

    “The algorithms do this by monitoring the amount of time particular kinds of content keep the particular user engaged with the platform, and they use that data to continuously adjust the content so that the particular user remains engaged with the platform for ever lengthening periods of time”

    From Ethics of the Attention Economy: The Problem of Social Media Addiction (2021) · cites this paper as Lee, Hosanagar, & Nair, 2018

Cites

Flagged first, then by citations

5 of the 90 references couldn’t be matched to a known paper.

Research works printed but not linked: 10

  1. 10.1177/002224379703400304 · DOI
  2. Bagwell K, 2007, Handbook of Industrial Organization, 3, 1701
  3. Creamer M, 2012, AdAge.
  4. Ellickson PB, 2010, Quant. Marketing Econom., 10, 1
  5. 10.1177/002224299305700101 · DOI
  6. Liu X, Lee D, Srinivasan K (2017) Large scale cross category analysis of consumer review content on sales conversion leveraging deep learning. Working Paper 16-09, NET Institute, New York.
  7. Malik HH, 2011, Proc. 20th ACM Internat. Conf. Inform. Knowledge Management, 2497
  8. 10.2307/1250490 · DOI
  9. Terlep S, 2012, Wall Street Journal
  10. Weiss M, 2000, The Value of Brand Personalities: The Phenomenon of the Strategic Positioning of Brands

Cited by

Sorted by citations

Related

Authors
Lee, D., Hosanagar, K., & Nair, H. S.
Affiliations
  • Carnegie Mellon University (US)
  • University of Pennsylvania (US)
  • Stanford University (US)
ORCID
Venue
Management Science
Publisher
Institute for Operations Research and the Management Sciences (INFORMS)
Published
2018-11
Volume
64
Issue
11
Pages
5105-5131
ISSN
  • 0025-1909 (ISSN-L)
  • 1526-5501
DOI
10.1287/mnsc.2017.2902
OpenAlex
W3125510825
Semantic Scholar
49ae2abdba289d0823cf3440b4320a76e9a580c0
Cited by
1,069
References
90
Citations by year
2026: 109 · 2025: 141 · 2024: 155 · 2023: 138 · 2022: 158 · 2021: 146 · 2020: 87 · 2019: 69 · 2018: 29 · 2017: 16 · 2016: 8 · 2015: 11 · 2014: 2
FWCI
131.60
Type
journal article
Language
en
Open access
Locations
  • Management Science (publishedVersion)
  • SSRN Electronic Journal (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • ScholarlyCommons (University of Pennsylvania) (submittedVersion)
Topics
  • Social Sciences › Sociology and Political Science › Digital Marketing and Social Media
  • Social Sciences › Business, Management and Accounting › Marketing › Marketing and Advertising Strategies
  • Social Sciences › Business, Management and Accounting › Marketing › Consumer Market Behavior and Pricing
Keywords
social media advertising, advertising content, customer engagement, Facebook, brand personality, humor, emotions, conversion, behavioral targeting, natural language processing

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review