From 2,772 segments to five personas: Summarizing a diverse online audience by generating culturally adapted personas

Salminen, Joni; Şengün, Sercan; Kwak, Haewoon; Jansen, Bernard J.; An, Jisun; Jung, Sin‐Ho; Vieweg, Sarah; Harrell, D. Fox

doi:10.5210/fm.v23i6.8415

Cited by 31 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At its best, automatic data collection and analysis is cost-efficient and behaviorally accurate across the whole user base, providing excellent foundations for the creation of datadriven personas. Additionally, DDDPs do not necessarily need to be either quantitative or qualitative, but they can draw from both types of data, as demonstrated by Salminen, Şengün, et al (2018) with their hybrid personas created using quantitative online analytics data and qualitative insights.…”

Section: Evaluating Data-driven Personas In the Light Of Criticism: Dmentioning

confidence: 99%

“…Third, representativeness of the sample is not an issue, when the persona generation is based on the whole user base. For example, Salminen, Şengün, et al (2017) generated personas from YouTube data of a major online news media company consisting of millions of viewers. Using online analytics data potentially solves the trade-off of relying on either qualitatively rich but non-verifiable data or using numbers that are accurate but lose the immersion of another human being.…”

Section: Evaluating Data-driven Personas In the Light Of Criticism: Dmentioning

confidence: 99%

“…For example, (Liapis et al 2015) are able to infer dozens of behavioral gaming patterns from their dataset. Salminen, Şengün, et al (2018) summarize the audience of a large social media channel, consisting of viewers from more than 200 countries, to five representative personas. ) identify hundreds of unique content consumption patterns among channel users that they use to generate personas.…”

Section: Evaluating Data-driven Personas In the Light Of Criticism: Dmentioning

confidence: 99%

“…Free expression in social media provides opportunities to learn about the needs and traits of groups and individuals (Owusu et al 2016). Overall, the development of computational techniques and the availability of online data has resulted in an increased interest in datadriven personas: (a) to describe the content consumption patterns of diverse online audiences (Salminen, Şengün, et al 2018), and (b) to use online data, namely online analytics and social media posts, in persona generation Zhang, Brown & Shankar 2016).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Are personas done? Evaluating their usefulness in the age of digital analytics

Salminen¹,

Jansen²,

An³

et al. 2018

Pers Stud

Self Cite

View full text Add to dashboard Cite

In this critique, we conceptually examine the use of personas in an age of availability of large-scale online analytics data. Based on the criticism and benefits outlined in prior work, we formulate the major arguments for and against the use of personas, analyze these arguments, and demonstrate areas for the productive employment of personas by leveraging digital analytics data in their creation. From our review of the prior literature and the given availability of online customer data, our key tenet is that personas are located between aggregated and individual statistics. At their best, personas capture the coverage of the customer base attributed to aggregated data representations while retaining the interpretability of individual-level analytics. Persona creation benefits from both novel computational techniques and data sources. To demonstrate this, we propose and implement automatically generated personas primarily based on quantitative data. We also review key persona validation issues and examine how these issues can be addressed with automated persona generation using real user data from online analytics platforms. Finally, we outline areas of future research in the persona domain within the field of digital marketing and advertising. Overall, to survive in the rapidly developing marketing industry and online customer analytics, personas must evolve by adopting new practices. There are implications for this evolution of personas in a variety of domains, including design, content creation, and digital marketing.

show abstract

Section: Evaluating Data-driven Personas In the Light Of Criticism: Dmentioning

confidence: 99%

Section: Evaluating Data-driven Personas In the Light Of Criticism: Dmentioning

confidence: 99%

Section: Evaluating Data-driven Personas In the Light Of Criticism: Dmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Are personas done? Evaluating their usefulness in the age of digital analytics

Salminen¹,

Jansen²,

An³

et al. 2018

Pers Stud

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, by studying UGC, different results can be obtained more readily than with traditional survey research. Additionally, customer information from social media can be collected in real-time and more cost-effectively than with more traditional data collection methods (Salminen, Şengün, Kwak, Jansen, An, Jung, Vieweg and Harrell, 2018). Social media platforms provide access to timely data, making it possible for companies to monitor their online corporate reputations (Gensler et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Classifying online corporate reputation with machine learning: a study in the banking domain

Rantanen

Salminen

Ginter

et al. 2019

INTR

Self Cite

View full text Add to dashboard Cite

Purpose User-generated social media comments can be a useful source of information for understanding online corporate reputation. However, the manual classification of these comments is challenging due to their high volume and unstructured nature. The purpose of this paper is to develop a classification framework and machine learning model to overcome these limitations. Design/methodology/approach The authors create a multi-dimensional classification framework for the online corporate reputation that includes six main dimensions synthesized from prior literature: quality, reliability, responsibility, successfulness, pleasantness and innovativeness. To evaluate the classification framework’s performance on real data, the authors retrieve 19,991 social media comments about two Finnish banks and use a convolutional neural network (CNN) to classify automatically the comments based on manually annotated training data. Findings After parameter optimization, the neural network achieves an accuracy between 52.7 and 65.2 percent on real-world data, which is reasonable given the high number of classes. The findings also indicate that prior work has not captured all the facets of online corporate reputation. Practical implications For practical purposes, the authors provide a comprehensive classification framework for online corporate reputation, which companies and organizations operating in various domains can use. Moreover, the authors demonstrate that using a limited amount of training data can yield a satisfactory multiclass classifier when using CNN. Originality/value This is the first attempt at automatically classifying online corporate reputation using an online-specific classification framework.

show abstract

Combining Behaviors and Demographics to Segment Online Audiences: Experiments with a YouTube Channel

et al. 2018

Self Cite

View full text Add to dashboard Cite

Social media channels with audiences in the millions are increasingly common. Efforts at segmenting audiences for populations of these sizes can result in hundreds of audience segments, as the compositions of the overall audiences tend to be complex. Although understanding audience segments is important for strategic planning, tactical decision making, and content creation, it is unrealistic for human decision makers to effectively utilize hundreds of audience segments in these tasks. In this research, we present efforts at simplifying the segmentation of audience populations to increase their practical utility. Using millions of interactions with hundreds of thousands of viewers with an organization's online content collection, we first isolate the maximum number of audience segments, based on behavioral profiling, and then demonstrate a computational approach of using non-negative matrix factorization to reduce this number to 42 segments that are both impactful and representative segments of the overall population. Initial results are promising, and we present avenues for future research leveraging our approach.

show abstract

From 2,772 segments to five personas: Summarizing a diverse online audience by generating culturally adapted personas

Cited by 31 publications

References 0 publications

Are personas done? Evaluating their usefulness in the age of digital analytics

Are personas done? Evaluating their usefulness in the age of digital analytics

Classifying online corporate reputation with machine learning: a study in the banking domain

Combining Behaviors and Demographics to Segment Online Audiences: Experiments with a YouTube Channel

Contact Info

Product

Resources

About