Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting
Open accessThe DOI matches its Crossref record; 92 of the 98 references it cites were found in a registry or an index; 1 of the 15 sources its claims cite were checked for support.
Abstract
The advertising systems and the algorithms they use are constantly evolving and expanding the possibilities for reaching potential customers. Hyper-targeting (also called microtargeting) is the use of detailed customer data and marketing automation to deliver highly targeted and personalized messages across a large number of channels. These campaigns are designed to appeal to specific people or small groups of customers. By using the ability to process large amounts of data through innovations, such as predictive analytics, marketers can gain a deeper understanding of their audiences, focusing on specific accounts and not on the entire segments. This reportedly allows B2B brands to target customers directly and provide unique personal and highly relevant experiences. However, the scientific evidence to support this claim is missing. Some previous studies even suggest a negative impact of highly personalized advertising content on user reactiveness and purchase behavior. In this article, we test the effects of different levels of personalized advertisements using the advanced campaign targeting tool called Facebook Lookalike Audiences. Facebook Lookalike Audiences works on the basis of the estimation of customer similarity based on the characteristics of a custom audience, as defined by the advertiser. We examine the performance of various targeting settings using data from 840 Facebook ads with different personalization levels. These advertisements are compared in terms of reach, number of reactions, frequency of impressions, number of clicks, average time spent on a website, number of viewed pages, number of conversions, and profitability. We believe that the findings presented in this article help clarify the factors that influence user reactiveness toward personalized online advertising using evidence from actual Facebook ad sets.
Overview
CoChat Summary
## TL;DR
The paper tests whether Facebook Lookalike Audiences and varying personalization levels improve ad performance, using 840 real Facebook ads from an e-shop. It finds that moderate personalization performed best, while the most highly personalized ads were not always the most effective and could trigger less favorable reactions.
## Key findings
- The study analyzed 840 Facebook ads and found that hyper-targeting has limits; the authors report that it may lead to negative attitudes toward the advertiser.
- For customer segmentation, Facebook performance data processed by Facebook’s internal algorithm performed best, reaching 11.68 EUR average profitability.
- Across segmentation methods, newsletter subscribers processed by Apriori produced 10.84 EUR average profitability, and average customer value processed by Apriori produced 10.53 EUR; the lowest averages were web traffic (9.95 EUR) and clustering algorithm (10.04 EUR).
- Personalized ads were most effective at the conversion stage (12.00 EUR), followed by consideration (10.23 EUR), and were least effective for awareness (8.84 EUR).
- The paper reports that placement did not influence the impact of personalized ads: Facebook newsfeed, Marketplace, and Messenger were similar, while Instagram newsfeed was lower at 9.98 EUR.
- By gender, the average profitability was 9.76 EUR for females and 9.91 EUR for males; the authors say males reacted more positively at several personalization levels, while females were more sensitive to highly personalized content.
## Methods
- The authors ran an online field experiment using the advertising accounts of a Czech e-shop selling home accessories and kitchen equipment, with real-life campaigns.
- They created 840 Facebook ads using Facebook Custom Audiences (CA) and Lookalike Audiences (LA), with 10 levels of personalization, 3 conversion stages (awareness, consideration, conversion), and 4 placements (Facebook newsfeed, Messenger, Facebook marketplace, Instagram newsfeed).
- They used two segmentation methods (Apriori and clustering) and four data sources (average customer value, newsletter subscription, web traffic, internal Facebook data), then analyzed the results in SPSS Statistics v26 using average profitability as the main outcome.
## Limitations
- The paper explicitly says the experiment “may be considered as a pilot study” because the authors could not find comparable prior research using actual Facebook campaign data with Lookalike Audiences.
- It also states that the results cannot be compared with other findings on personalized advertising because similar research was not available in the scientific literature.
- Evident from the text: the study is based on one e-store and Facebook ads only, so generalization beyond this setting is not directly supported by the paper.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
0 Valid · 0 Not valid · 8 Not checked · 34 Own results and interpretations
None of the sources cited for this claim have been checked yet.
In the paper
“The only two papers we found that used data from actual advertising campaigns with LA were Akers and Gordon [104] and Kovčo et al. [94].”
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > VI. DISCUSSION
What the sources say
- Could not verifycites [104] 104. L. Akers and J. S. Gordon, ''Using Facebook for large-scale online randomized clinical trial recruitment: Effective advertising strategies,'' J. Med. Internet Res., vol. 20, no. 11, p. e290, 2018. doi: 10.2196/jmir. 9372. TEREZA SEMERÁDOVÁ is a Research Assis- tant with the Department of Informatics, Techni- cal University of Liberec. In addition to academic activities, she also participates in numerous mar- keting projects where she operates as a consultant on Facebook ads, Google adwords, and website analytics. is She is a specialist in dynamic ads and remarketing. Her primary research sourceExperimental — accuracy not yet measured
Our copy under DOI 10.2196/jmir is not a research article but the JMIR Medical Informatics journal homepage listing (recent-article teasers, open-peer-review preprints, impact-factor/CiteScore statements); no section, page or passage addresses advertising-campaign data, latent attributes/LA, or the cited works. Searches for 'Akers Gordon advertising campaign data', 'Kovčo et al. real-world campaign', and 'latent attribute advertising data review' returned only unrelated listings (COPD LLM advice, AI scribe implementation reports, EHR deidentification, triage vignettes). Nothing in our copy supports or contradicts the claim, so it cannot be audited against this source. (LLM, conf=0.70)
- Not checked yetcites [94] 94. A. Kovčo, P. Vranečić, and K. Aleksić-Maslać, ''Advantages of WCA Facebook advertising with analysis and comparison of efficiency to clas- sic Facebook advertising,'' WSEAS Trans. Bus. Econ., vol. 15, no. 1, pp. 73-79, 2018. source
Checked before — its earlier verdict is held back until a new check runs.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In addition, the individual results show inconsistent performance of the placements for different personalization levels.”
- Also stated in: § VI. DISCUSSION · plain
“The data from our experiment did not show any relation between placement and the level of personalization.”
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > RQ4: What is the relationship between the level of personalization and conversion stage of the customer conversion funnel?
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § VI. DISCUSSION · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The results indicate that CA derived from Facebook performance data and processed by internal Facebook algorithm performed the best by reaching 11.68 EUR average profitability (see Table 2).”
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > V. DATA ANALYSIS
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“CA based on newsletter subscribers processed by an Apriori algorithm produced the second-highest profitability (10.84 EUR)”
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > V. DATA ANALYSIS
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We can see that the highest profitability was reached by ads with a medium level (5 and 6) of personalization.”
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > V. DATA ANALYSIS
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
24 more claims
Create a free account to see all 42 claims and to verify the 1 reference still open.
- The quote only partly states this claim. 1
- Probably not a substantial claim. 7
- It may state two separate claims as one. 7
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > RQ4: What is the relationship between the level of personalization and conversion stage of the customer conversion funnel?
“In Table 6, we can see that the average profitability is slightly higher for females (9.76 EUR) than for males (9.91 EUR);”
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > RQ4: What is the relationship between the level of personalization and conversion stage of the customer conversion funnel?
“In Table 6, we can see that the average profitability is slightly higher for females (9.76 EUR) than for males (9.91 EUR);”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > A. RESEARCH FRAMEWORK
“As we stated earlier, we set five main research questions related to the analysis of effects of hyper-targeting on advertising performance.”
§ Computer Estimation of Customer Similarity With Facebook Lookalikes: Advantages and Disadvantages of Hyper-Targeting > A. RESEARCH FRAMEWORK
“RQ6: Does the perception of the personalized ads differ with respect to the age and gender of users?”
Citations
Cites
Sambamurthy, V., Bharadwaj, A., & Grover, V. (2003) · MIS Quarterly · doi:10.2307/30036530 · Cited by 3,228
Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management
Linoff, G. S., & Berry, M. J. (2004) · Cited by 1,232
How Unique Is Your Web Browser?
Eckersley, P. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-14527-8_1 · Cited by 756
Trending: The Promises and the Challenges of Big Social Data
Manovich, L. (2012) · Debates in the Digital Humanities · doi:10.5749/minnesota/9780816677948.003.0047 · Cited by 682 · cited 2×
“[17] L. Manovich, ‘‘Trending: The promises and the challenges of big social data,’’ in Debates in the Digital Humanities, vol. 2.”
BackgroundBaruh, L., Secinti, E., & Cemalcilar, Z. (2017) · Journal of Communication · doi:10.1111/jcom.12276 · Cited by 618 · cited 1×
“[76] found a contradictory relationship between users’ beliefs about privacy”
BackgroundSocial Media Analytics and Intelligence
Zeng, D., Chen, H., Lusch, R., & Li, S.-H. (2010) · IEEE Intelligent Systems · doi:10.1109/mis.2010.151 · Cited by 582 · cited 1×
“closely to all their needs and desires [10,11,12,13].”
BackgroundThe Importance of Trust for Personalized Online Advertising
Bleier, A., & Eisenbeiss, M. (2015) · Journal of Retailing · doi:10.1016/j.jretai.2015.04.001 · Cited by 529 · cited 2×
“In addition, Bleier and Eisenbeiss [95] presented the results of their lab study showing that more trusted retailers can increase the effectiveness of their ads by very narrow targeting without generating privacy concerns.”
BackgroundInfluentialHow to create a realistic customer journey map
Rosenbaum, M. S., Otalora, M. L., & Ramírez, G. C. (2017) · Business Horizons · doi:10.1016/j.bushor.2016.09.010 · Cited by 441 · cited 1×
“Such interactive events are called touchpoints and represent potential areas for further innovation [22].”
BackgroundMobile advertising: A framework and research agenda
Grewal, D., Bart, Y., Spann, M., & Zubcsek, P. P. (2016) · Journal of Interactive Marketing · doi:10.1016/j.intmar.2016.03.003 · Cited by 316 · cited 1×
“Many researchers have already tested the impact of exclusively tailored advertising in traditional media [63], [64], in the online environment including social media and websites [65], [66], and in the context of mobile devices [67], [68].”
BackgroundShanahan, T., Tran, T. P., & Taylor, E. C. (2019) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2018.10.007 · Cited by 310
Jung, A.-R. (2017) · Computers in Human Behavior · doi:10.1016/j.chb.2017.01.008 · Cited by 289
Targeting in advertising markets: implications for offline versus online media
Bergemann, D., & Bonatti, A. (2011) · The RAND Journal of Economics · doi:10.1111/j.1756-2171.2011.00143.x · Cited by 258
Personalized ads on Facebook: An effective marketing tool for online marketers
Tran, T. P. (2017) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2017.06.010 · Cited by 186
Mapping the customer journey: Lessons learned from graph-based online attribution modeling
Anderl, E., Becker, I., von Wangenheim, F., & Schumann, J. H. (2016) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2016.03.001 · Cited by 186
Understanding ad avoidance on Facebook: Antecedents and outcomes of psychological reactance
Youn, S., & Kim, S. (2019) · Computers in Human Behavior · doi:10.1016/j.chb.2019.04.025 · Cited by 185 · cited 1×
“sified competition push companies to put more effort into preparing creative content for their ads and finding innovative approaches to ad optimization to minimize the marketing costs [6], [7].”
BackgroundTransportation sentiment analysis using word embedding and ontology-based topic modeling
Ali, F., Kwak, D., Khan, P., El-Sappagh, S., Ali, A., Ullah, S., Kim, K. H., & Kwak, K.-S. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.02.033 · Cited by 183 · cited 1×
“Alternatively, sentiment scale measuring may also be used [40], [41].”
MethodSentiment Analysis in Social Networks
(2017) · Elsevier eBooks · doi:10.1016/c2015-0-01864-0 · Cited by 182
Retail business analytics: Customer visit segmentation using market basket data
Griva, A., Bardaki, C., Pramatari, K. C., & Papakiriakopoulos, D. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.01.029 · Cited by 180
Bang, H., & Wojdynski, B. W. (2016) · Computers in Human Behavior · doi:10.1016/j.chb.2015.10.025 · Cited by 174 · cited 5×
“As mentioned by Bang and Wojdynski [71], personalized ads are”
BackgroundInfluentialDynamic Organizations: Achieving Marketplace And Organizational Agility With People
Dyer, L., & Shafer, R. A. (2003) · eCommons (Cornell University) · Cited by 168
How different information types affect viewer’s attention on internet advertising
Hsieh, Y.-C., & Chen, K.-H. (2011) · Computers in Human Behavior · doi:10.1016/j.chb.2010.11.019 · Cited by 158 · cited 11×
“[59] Y. H. Huang and C. T. Chen, ‘‘The improvement of customer satisfaction by adopting CRM technology,’’ JTB J. Technol.”
BackgroundInfluentialData sharing and interoperability: Fostering innovation and competition through APIs
Borgogno, O., & Colangelo, G. (2019) · Computer Law & Security Review · doi:10.1016/j.clsr.2019.03.008 · Cited by 155 · cited 1×
“We already have sufficient capabilities (hardware and software) to process, store, organize, and evaluate them, but unfortunately, this is not accessible to third parties [32,33,34].”
BackgroundEffects of social media on firm value for U.S. restaurant companies
Kim, S., Koh, Y., Cha, J., & Lee, S. (2015) · International Journal of Hospitality Management · doi:10.1016/j.ijhm.2015.05.006 · Cited by 154 · cited 1×
“In addition, one of Klout’s most important functions is the ability to determine the topics within which users are influencers [38], [39].”
BackgroundMarketing analytics: Methods, practice, implementation, and links to other fields
France, S. L., & Ghose, S. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.11.002 · Cited by 154 · cited 1×
“Results from social media analysis significantly influence company marketing decisions [28].”
BackgroundMobile users’ information privacy concerns and the role of app permission requests
Degirmenci, K. (2020) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2019.05.010 · Cited by 151 · cited 1×
“however, the general findings confirm significant effects of prior privacy experience, computer anxiety, and perceived control in privacy concerns [99].”
Aspect based fine-grained sentiment analysis for online reviews
Tang, F., Fu, L., Yao, B., & Xu, W. (2019) · Information Sciences · doi:10.1016/j.ins.2019.02.064 · Cited by 150 · cited 1×
“Alternatively, sentiment scale measuring may also be used [40], [41].”
MethodSetyani, V., Zhu, Y., Hidayanto, A. N., Sandhyaduhita, P. I., & Hsiao, B. (2019) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2019.01.007 · Cited by 146 · cited 1×
“[72] explored users’ intrinsic motivations in reacting to social media ads.”
BackgroundOnline advertising: Analysis of privacy threats and protection approaches
Estrada-Jiménez, J., Parra‐Arnau, J., Rodríguez-Hoyos, A., & Forné, J. (2016) · Computer Communications · doi:10.1016/j.comcom.2016.12.016 · Cited by 142
iSpy? Tailored versus Invasive Ads and Consumers’ Perceptions of Personalized Advertising
Gironda, J. T., & Korgaonkar, P. K. (2018) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2018.03.007 · Cited by 137 · cited 3×
“On the other hand, Gironda and Korgaonkar [66] suggested that a number of factors, such as invasiveness, privacy control, perceived usefulness, and consumer innovativeness, are part of the user cognitive process when users are confronted with micro-targeted ads.”
BackgroundLooking for the perfect tweet. The use of data mining techniques to find influencers on twitter
Lahuerta-Otero, E., & Cordero-Gutiérrez, R. (2016) · Computers in Human Behavior · doi:10.1016/j.chb.2016.07.035 · Cited by 135 · cited 1×
“In addition, one of Klout’s most important functions is the ability to determine the topics within which users are influencers [38], [39].”
BackgroundCustomer Engagement Through Personalization and Customization
Bleier, A., Keyser, A. D., & Verleye, K. (2017) · Springer eBooks · doi:10.1007/978-3-319-61985-9_4 · Cited by 134
A Big Data Clustering Algorithm for Mitigating the Risk of Customer Churn
Bi, W., Cai, M., Liu, M., & Li, G. (2016) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2016.2547584 · Cited by 133 · cited 1×
“Therefore, scholars and advertisers have looked for new approaches to interpret online marketing data in the business context of the company [25,26,27].”
BackgroundA dynamic capability view of marketing analytics: Evidence from UK firms
Cao, G., Duan, Y., & El Banna, A. (2019) · Industrial Marketing Management · doi:10.1016/j.indmarman.2018.08.002 · Cited by 130 · cited 1×
“data sources into one integrated marketing analysis, since the separate evaluation of each data source may lead to differing results [29].”
ResultYu, C., Zhang, Z., Lin, C., & Wu, Y. J. (2020) · Industrial Marketing Management · doi:10.1016/j.indmarman.2019.05.001 · Cited by 124 · cited 1×
“[69] created a conceptual model of customer reactions based on personalized ads and their click-through intentions.”
BackgroundVisual opinion analysis of customer feedback data
Oelke, D., Hao, M., Rohrdantz, C., Keim, D. A., Dayal, U., Haug, L.-E., & Janetzko, H. (2009) · IEEE Conference on Visual Analytics Science and Technology (VAST) · doi:10.1109/vast.2009.5333919 · Cited by 123 · cited 1×
“With the advent of computers, SNA expanded into a discipline with its own approach to this paradigm, including clearly defined theory and analytical software [35,36,37].”
BackgroundAn Efficient CRM-Data Mining Framework for the Prediction of Customer Behaviour
Bahari, T. F., & Elayidom, M. S. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.02.136 · Cited by 117 · cited 3×
“Bahari and Elayidom [51] compared the effectiveness of two classifi-”
BackgroundInfluentialChen, Q., Feng, Y., Liu, L., & Tian, X. (2019) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2018.09.001 · Cited by 117 · cited 1×
“[75] referred to this phenomenon using the term personalization paradox.”
BackgroundWei, J.-T., Lee, M., Chen, H.-K., & Wu, H. (2013) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.07.053 · Cited by 116 · cited 1×
“[50] presented a case study that combined self-organizing maps (SOM), K-means methods, and the RFM model to create four segments of customers in a hair salon to propose customizedmarketing strategies for each segment.”
MethodLike or dislike? Adolescents’ responses to personalized social network site advertising
Walrave, M., Poels, K., Antheunis, M. L., Van den Broeck, E., & van Noort, G. (2018) · Journal of Marketing Communications · doi:10.1080/13527266.2016.1182938 · Cited by 112
Luo, X., Jiang, C., Wang, W., Yang, X., Wang, J., & Zhao, W. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2018.04.085 · Cited by 105 · cited 1×
“These accuracy parameters are often the touchstone of the issue [42,43,44,45].”
BackgroundTargeting customers for profit: An ensemble learning framework to support marketing decision-making
Lessmann, S., Haupt, J., Coussement, K., & Bock, K. W. D. (2019) · Information Sciences · doi:10.1016/j.ins.2019.05.027 · Cited by 105 · cited 1×
“[53] described a new profit-conscious modeling framework that operates on the basis of statistical learning principles.”
BackgroundApplications of data mining in retail business
Ahmed, S. (2004) · International Conference on Information Technology: Coding and Computing (ITCC) · doi:10.1109/itcc.2004.1286695 · Cited by 98
Sentiment Analysis in Social Networks
Fersini, E. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-804412-4.00006-1 · Cited by 98 · cited 1×
“These accuracy parameters are often the touchstone of the issue [42,43,44,45].”
BackgroundSchreiner, T., Rese, A., & Baier, D. (2019) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2019.02.010 · Cited by 92 · cited 1×
“However, the effects of personalization may differ depending on not only the products presented but also the intensity of recommendations and characteristics of the target segment [74].”
BackgroundThe role of IT in achieving operational agility: A case study of Haier, China
Huang, P., Ouyang, T. H., Pan, S. L., & Chou, T. (2012) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2012.02.001 · Cited by 88 · cited 1×
“[21], information technologies and systems stand at the center of these pro-agility activities by providing crucial data for innovative optimal customer solutions that are the key prerequisite for a company to succeed in the current highly competitive environment.”
BackgroundAkers, L., & Gordon, J. S. (2018) · Journal of Medical Internet Research · doi:10.2196/jmir.9372 · Cited by 87
Modeling of fuzzy-based voice of customer for business decision analytics
Aguwa, C. C., Olya, M. H., & Monplaisir, L. F. (2017) · Knowledge-Based Systems · doi:10.1016/j.knosys.2017.03.019 · Cited by 84 · cited 1×
“They have the power to bargain with producers and service providers over price and product/service characteristics [14,15,16].”
BackgroundRedondo, I., & Aznar, G. (2018) · Telematics and Informatics · doi:10.1016/j.tele.2018.04.008 · Cited by 80
Lee, J., Ham, C.-D., & Kim, M. (2013) · Journal of Interactive Advertising · doi:10.1080/15252019.2013.768048 · Cited by 76 · cited 1×
“Ad blockers as a tool can also allow users to moderate the kind of advertisements they receive [83], [80].”
BackgroundMeasuring the Facebook Advertising Ecosystem
Andreou, A., Silva, M., Benevenuto, F., Goga, O., Loiseau, P., & Mislove, A. (2019) · Proceedings 2019 Network and Distributed System Security Symposium · doi:10.14722/ndss.2019.23280 · Cited by 72 · cited 1×
“[101] and Wood [102] mention LA as one of the potential targeting options offered by Facebook to advertisers.”
BackgroundAnalyzing Customer Journey with Process Mining: From Discovery to Recommendations
Terragni, A., & Hassani, M. (2018) · International Conference on Future Internet of Things and Cloud (FiCloud) · doi:10.1109/ficloud.2018.00040 · Cited by 68 · cited 1×
“unresolved issues concerning the effectiveness of measurements of individual touchpoints [23].”
BackgroundA systematic mapping study of API usability evaluation methods
Rauf, I., Troubitsynå, E., & Porres, I. (2019) · Computer Science Review · doi:10.1016/j.cosrev.2019.05.001 · Cited by 67 · cited 1×
“We already have sufficient capabilities (hardware and software) to process, store, organize, and evaluate them, but unfortunately, this is not accessible to third parties [32,33,34].”
Background(2023) · doi:10.2196/jmir · Cited by 61
Information diffusion in mobile social networks: The speed perspective
Lu, Z., Wen, Y., & Cao, G. (2014) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2014.6848133 · Cited by 60 · cited 1×
“Many researchers have already tested the impact of exclusively tailored advertising in traditional media [63], [64], in the online environment including social media and websites [65], [66], and in the context of mobile devices [67], [68].”
BackgroundMarketing analytics using anonymized and fragmented tracking data
Kakatkar, C., & Spann, M. (2019) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2018.10.001 · Cited by 59 · cited 1×
“Therefore, scholars and advertisers have looked for new approaches to interpret online marketing data in the business context of the company [25,26,27].”
BackgroundSaidali, J., Rahich, H., Tabaa, Y., & Medouri, A. (2019) · Procedia Manufacturing · doi:10.1016/j.promfg.2019.02.316 · Cited by 59 · cited 1×
“Therefore, scholars and advertisers have looked for new approaches to interpret online marketing data in the business context of the company [25,26,27].”
BackgroundAnalytical affective design with ambient intelligence for mass customization and personalization
Jiao, J. R., Xu, Q., Du, J., Zhang, Y., Helander, M. G., Khalid, H. M., Helo, P., & Ni, C. (2007) · International Journal of Flexible Manufacturing Systems · doi:10.1007/s10696-008-9032-1 · Cited by 58 · cited 1×
“[55] proposed an association rule mining technique of mass customization and personalization con-”
MethodAn assessment framework of intuitionistic fuzzy network for C2B decision making
Thirumalai, C., & Senthilkumar, M. (2017) · 2017 4th International Conference on Electronics and Communication Systems (ICECS) · doi:10.1109/ecs.2017.8067861 · Cited by 58 · cited 2×
“Thirumalai and Senthilkumar [61] classified customer needs using an intuition-based fuzzy priority weighting vector.”
MethodLink prediction in weighted social networks using learning automata
Moradabadi, B., & Meybodi, M. R. (2018) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2017.12.006 · Cited by 56 · cited 1×
“These accuracy parameters are often the touchstone of the issue [42,43,44,45].”
BackgroundThe joint effects of customer participation in various new product development stages
Chang, W. (2018) · European Management Journal · doi:10.1016/j.emj.2018.11.002 · Cited by 50 · cited 1×
“closely to all their needs and desires [10,11,12,13].”
BackgroundCustomer demand prediction of service-oriented manufacturing incorporating customer satisfaction
Cao, J., Jiang, Z., & Wang, K. (2015) · International Journal of Production Research · doi:10.1080/00207543.2015.1067377 · Cited by 48 · cited 1×
“[60], who attempted to predict user demand in the service-oriented manufacturing sector.”
BackgroundMyAdChoices: Bringing Transparency and Control to Online Advertising
Parra-Arnau, J., Achara, J. P., & Castelluccia, C. (2017) · ACM Transactions on the Web · doi:10.1145/2996466 · Cited by 48
Collateral damage of Facebook third-party applications: a comprehensive study
Symeonidis, I., Biczók, G., Shirazi, F., Pérez‐Solà, C., Schroers, J., & Preneel, B. (2018) · Computers & Security · doi:10.1016/j.cose.2018.03.015 · Cited by 47 · cited 1×
“We already have sufficient capabilities (hardware and software) to process, store, organize, and evaluate them, but unfortunately, this is not accessible to third parties [32,33,34].”
BackgroundRecommendations-based on semantic analysis of social networks in learning environments
Khaled, A., Ouchani, S., & Chohra, C. (2018) · Computers in Human Behavior · doi:10.1016/j.chb.2018.08.051 · Cited by 47 · cited 1×
“These accuracy parameters are often the touchstone of the issue [42,43,44,45].”
BackgroundRecommending products to customers using opinion mining of online product reviews and features
Rajeev, P. V., & Rekha, V. S. (2015) · 2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015] · doi:10.1109/iccpct.2015.7159433 · Cited by 46 · cited 1×
“closely to all their needs and desires [10,11,12,13].”
BackgroundOnline Advertisement, Optimization and Stochastic Networks
Tan, B., & Srikant, R. (2012) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2012.2195810 · Cited by 40 · cited 1×
“sified competition push companies to put more effort into preparing creative content for their ads and finding innovative approaches to ad optimization to minimize the marketing costs [6], [7].”
BackgroundState-of-the-art review of customer to business (C2B) model
Zhang, X., Ming, X., Liu, Z., et al. (2019) · Computers & Industrial Engineering · doi:10.1016/j.cie.2019.04.039 · Cited by 40 · cited 1×
“They have the power to bargain with producers and service providers over price and product/service characteristics [14,15,16].”
BackgroundThe Relationship between E-Lifestyle and Internet Advertising Avoidance
Abedini Koshksaray, A., Franklin, D., & Heidarzadeh Hanzaee, K. (2015) · Australasian Marketing Journal · doi:10.1016/j.ausmj.2015.01.002 · Cited by 37 · cited 1×
“[85] described the influence of e-lifestyle on ad reactance.”
BackgroundWang, Y., & Tseng, M. M. (2013) · IEEE Transactions on Engineering Management · doi:10.1109/tem.2013.2248729 · Cited by 34 · cited 3×
“M. Tseng, ‘‘Identifying emerging customer requirements in an early design stage by applying bayes factor-based sequential analysis,’’ IEEE Trans.”
BackgroundInfluentialContextual Internet Multimedia Advertising
Mei, T., & Hua, X. (2010) · Proceedings of the IEEE · doi:10.1109/jproc.2009.2039841 · Cited by 34 · cited 1×
“Many researchers have already tested the impact of exclusively tailored advertising in traditional media [63], [64], in the online environment including social media and websites [65], [66], and in the context of mobile devices [67], [68].”
BackgroundAdaptive look-alike targeting in social networks advertising
Popov, A. S., & Iakovleva, D. (2018) · Procedia Computer Science · doi:10.1016/j.procs.2018.08.264 · Cited by 28
Applying data mining for online CRM marketing strategy
Chiang, W. (2018) · British Food Journal · doi:10.1108/bfj-02-2017-0075 · Cited by 26 · cited 1×
“Chiang [49] used data mining with fuzzy clustering and Apriori algorithm to explore customer databases and acquire more marketing and purchasing information.”
MethodAn approach to identify user preferences based on social network analysis
Milovanović, S., Bogdanović, Z. M., Лабус, А., Barać, D., & Despotovic-Zrakic, M. S. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2018.10.028 · Cited by 26 · cited 1×
“With the advent of computers, SNA expanded into a discipline with its own approach to this paradigm, including clearly defined theory and analytical software [35,36,37].”
BackgroundPrivacy-preserving and advertising-friendly web surfing
Sánchez, D., & Viejo, A. (2018) · Computer Communications · doi:10.1016/j.comcom.2018.09.002 · Cited by 24 · cited 1×
“Ad blockers as a tool can also allow users to moderate the kind of advertisements they receive [83], [80].”
BackgroundCustomer interface design for customer co-creation in the social era
Kang, J. M. (2017) · Computers in Human Behavior · doi:10.1016/j.chb.2017.03.032 · Cited by 20 · cited 1×
“closely to all their needs and desires [10,11,12,13].”
BackgroundErtugan, A. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.11.220 · Cited by 20
MyAdChoices: Bringing Transparency and Control to Online Advertising
Parra-Arnau, J., Achara, J. P., & Castelluccia, C. (2016) · arXiv · doi:10.48550/arxiv.1602.02046 · Cited by 20
Segmenting customers with data mining techniques
Güllüoğlu, S. S. (2015) · doi:10.1109/dinwc.2015.7054234 · Cited by 17 · cited 2×
“All were segmented using Apriori algorithm, as described by Güllüoğlu [91] and Silva et al.”
MethodCultural differences affect interactive television advertising
Zorn, S. F., Bellman, S., Robinson, J. A., & Varan, D. (2013) · Journal of Marketing Communications · doi:10.1080/13527266.2013.833539 · Cited by 16 · cited 1×
“[77] argued that aspects of the cultural and political environment are also involved in the”
BackgroundAdvertising Insertion in Sports Webcasts
Wan, K.-W., & Yan, X. (2007) · IEEE Multimedia · doi:10.1109/mmul.2007.26 · Cited by 15 · cited 1×
“Many researchers have already tested the impact of exclusively tailored advertising in traditional media [63], [64], in the online environment including social media and websites [65], [66], and in the context of mobile devices [67], [68].”
BackgroundLi, C., & Liu, J. (2017) · Computers in Human Behavior · doi:10.1016/j.chb.2017.04.031 · Cited by 14 · cited 6×
“Li and Liu [73] claimed that simple, personalized adjust-”
BackgroundInfluentialBuilding social computing system in big data: From the perspective of social network analysis
Liao, C. H., & Chen, M. (2018) · Computers in Human Behavior · doi:10.1016/j.chb.2018.09.040 · Cited by 13 · cited 1×
“With the advent of computers, SNA expanded into a discipline with its own approach to this paradigm, including clearly defined theory and analytical software [35,36,37].”
BackgroundCustomer segmentation analysis based on SOM clustering
Li, Y., & Lin, F. (2008) · IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI) · doi:10.1109/soli.2008.4686353 · Cited by 9 · cited 1×
“[92], and clustering algorithm, as explained by Li and Li [93].”
MethodAssociation Rule Mining for Customer Segmentation in the SMEs Sector Using the Apriori Algorithm
Silva, J., Angulo, M. G., Cabrera, D., et al. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9942-8_46 · Cited by 7 · cited 1×
“[92], and clustering algorithm, as explained by Li and Li [93].”
MethodCalculation of Facebook Marketing Effectiveness in Terms of ROI
Semerádová, T., & Weinlich, P. (2019) · Advances in Marketing, Customer Relationship Management, and E-Services · doi:10.4018/978-1-5225-7344-9.ch014 · Cited by 6 · cited 3×
“level of profitability or even increasing it [3].”
BackgroundSelf-citationA Voucher-Integrated Trading Model for C2B and C2C E-Commerce System Development
Iguchi, M., Terada, M., Nakamura, Y., et al. (2003) · IFIP advances in information and communication technology · doi:10.1007/978-0-387-35617-4_27 · Cited by 5
Extracting Customer Traces from CRMS: From Software to Process Models
Osman, C.-C., & Ghiran, A.-M. (2019) · Procedia Manufacturing · doi:10.1016/j.promfg.2019.02.261 · Cited by 5
Facebook Analytics, Advertising, and Marketing
Yu, D., & Houg, A. (2014) · Facebook Nation · doi:10.1007/978-1-4939-1740-2_6 · Cited by 4 · cited 3×
“In 2014, Yu and Houg [100] discussed the potential of LA”
BackgroundInfluentialIntelligent need acquisition approach for heterogeneous customers under online mass customization
Zhang, X. (2012) · Cited by 4
Kovco, A., Aleksić-Maslać, K., & Vranešić, P. (2017) · The Internet of Things · Cited by 4
Boosting pay-per-click performance by combining search and social audience data
Wood, B. (2018) · Journal of digital & social media marketing. · doi:10.69554/banl6081 · Cited by 3 · cited 3×
“Similarly, Andreou et al. [101] and Wood [102] mention LA as one of the potential targeting options offered by Facebook to advertisers.”
BackgroundWu, Q., & Guo, Y. (2013) · DOAJ (DOAJ: Directory of Open Access Journals) · Cited by 2
Barbero (2014) · doi:10.1016/j · Cited by 1
Research works printed but not linked: 14
- rosemann, 2012, Leveraging social network data for analytical CRM strategies—The introduction of social BI, Proc ECIS, 1
- wiener, 1956, Cybernétique et Société
- 2019, Understand Attribution Results
- huang, 2015, The improvement of customer satisfaction by adopting CRM technology, JTB J Technol Bus, 120, 1
- 2019, About Advertising Objectives on Facebook
- 2019, Facebook Active Advertisers 2019
- 2019, About Lookalike Audiences for Facebook ADS
- shmueli, 2017, Data Mining for Business Analytics Concepts Techniques and Applications in R
- ládrová, 2018, New Facebook Algorithm How Does It Affect Sponsored Posts? IDIMT-2018 Strategic Modeling in Management Economy and Society, 225
- 2019, Facebook Advertising Targeting Options
- swan, 2019, The New Facebook Algorithm |5 Tips to Master It In 2019
- 2019, Custom Audiences
- 2019, Create a Lookalike Audience |Facebook Ads Help Centre
- 2019, Create A Custom Audience From A Customer List |Facebook Ads Help Centre
Cited by
Han, R., Lam, H. K. S., Zhan, Y., Wang, Y., Dwivedi, Y. K., & Tan, K. H. (2021) · Industrial Management & Data Systems · doi:10.1108/imds-05-2021-0300 · Cited by 165
Rane, N., Choudhary, S. P., & Rane, J. (2023) · Social Science Research Network · doi:10.2139/ssrn.4641044 · Cited by 51
Mühlhoff, R., & Willem, T. (2023) · Big Data & Society · doi:10.1177/20539517231156127 · Cited by 51
Abrantes, B. F., & Ostergaard, K. G. (2021) · Journal of Marketing Analytics · doi:10.1057/s41270-021-00144-5 · Cited by 22
“…gives attention to an exhaustive utilization of detailed customer-data and marketing automation tools, based on predictive modeling, statistical tools, and algorithms to target and deliver highly personalized messages across a large number of digital channels (Semerádová and Weinlich 2019).”
BackgroundRogić, S., Kašćelan, L., & Bach, M. P. (2022) · Journal of theoretical and applied electronic commerce research · doi:10.3390/jtaer17030051 · Cited by 22
“Online channels also generate detailed customer data that allow the companies to shape customised and targeted messages and deliver them through various channels [22].”
Background
Metadata
- Authors
- Semeradova, T., & Weinlich, P.
- Affiliations
- Technical University of Liberec (CZ)
- Venue
- IEEE Access
- Published
- 2019
- Volume
- 7
- Pages
- 153365-153377
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2981405027
- Cited by
- 39
- References
- 98
- Citations by year
- 2026: 5 · 2025: 7 · 2024: 4 · 2023: 10 · 2022: 4 · 2021: 5 · 2020: 4
- FWCI
- 6.55
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Technical University of Liberec through competitiveness of the company in the digital environment (SGS-2019-1068)
- Technology Agency of the Czech Republic under the Program of Applied Research ZETA through developing the skills necessary for the digital business transformation (TJ02000206)
- Technology Agency of the Czech Republic under the Program of Applied Research ZETA through developing skills necessary for digital business transformation
- Topics
- Social Sciences › Business, Management and Accounting › Marketing › 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
- microtargeting, personalized advertising, customer similarity, customer data, predictive analytics, B2B marketing, conversion rate
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.



