人物誌 (Persona) 為被廣泛使用的一項設計工具，其常用領域包括行銷、設計、資訊系統和商業產品等。在設計過程中使用人物誌有助於了解用戶的需求、體驗、行為和目標；然而，傳統人物誌在創建以及使用上遇到不少困難與限制，例如製作過程耗時、可能受研究人員偏見影響、可信度低、難以驗證代表性等等。近年來，在創建人物誌的過程加入量化方法顯得越來越常見且被重視，但大部分方法僅使用了傳統的敘述性統計方法像是集群分析，儘管改善了部分質化人物誌的限制，卻存在集群結果所創建的人物誌僅代表現有使用者而不是目標使用者或所需使用者等問題。如果創建的人物誌無法很好的代表目標用戶，則該人物誌便無法有效的被決策者接受，這將會浪費了在創建人物誌上所花費的時間和人力成本。在先前研究中，利用資料探勘為基礎的預測性方法來創建人物誌顯少被提及，但透過預測性的方法可以加強人物誌對於目標群體描繪的準確性以及可信度，且能夠預測非現有使用者的需求，因此我們提出創建預測性人物誌 (Predictive Persona) 的過程，並且比較了傳統量化人物誌創建和我們提出的預測性人物誌的創建過程。本研究向寵物飼主進行了問卷調查，問卷內容包括與之相關的個人屬性、寵物照護以及人口統計問項，接著通過應用傳統量化和預測方法分別生成了兩種類型的人物誌。我們將傳統量化人物誌定義為在構建過程中使用非監督式方法例如集群 (Clustering) 所生成的人物誌; 而預測性人物誌則為在創建過程中使用監督式方法例如羅吉斯回歸 (Logistic Regression) 所生成。集群方法生成的傳統量化人物誌更著重於在過去數據中尋找相似的群體，而預測性人物誌更側重於以數據的方法匡列出目標客群以及他們的特性與樣貌。傳統的量化人物誌和預測性人物誌可適用於不同的場景，傳統的量化人物誌更適合廣泛的針對不同群體描繪其輪廓以利決策者提供客制化的服務與設計，而預測性人物誌較適用於針對特定目標群體的決策 (例如預計購買客群)。透過在人物誌創建的過程加入預測性方法，本研究改善了質化以及傳統量化人物誌所面臨的困難點，提供了人物誌創建者一種新的預測性量化人物誌創建方法。

Personas have been a widely used tool among several designing fields, including marketing, designing, IT systems, and commercial products. Using personas in the designing process helps understand user’s needs, experiences, behaviors, and goals; however, several difficulties of traditional personas have been raised under the usage, such as it’s time-consuming and may be biased by the creators, having low credibility and not representative. Quantitative ways of creating personas have been gaining importance in recent years; however, most of them are using descriptive methods such as clustering. Although it improves some of the difficulties of qualitative persona creation, there are problems that the clustering results may not reflect the goals of end-users, and the created persona only represents the existing users rather than the desired users. If the created persona cannot well represent the target user, the created persona cannot be effectively accepted by the decision-makers, which will waste the time and cost of its creation. Few publications can be found in works of literature that discuss the usage of prediction methods in personas which we believe can improve the accuracy and credibility of personas and be used to predict new customers. Therefore, the approach of adding predictive algorithms in the persona creation process was proposed in this study. An online survey was launched to pet owners, questioning their personal attributes, pet care, and also demographic information. Two types of personas were generated by applying traditional quantitative and predictive methods. We define traditional quantitative personas as using unsupervised methods in the building process such as clustering; predictive personas as using supervised methods such as Logistic Regression. Compared to personas generated from clustering methods which focused more on finding groups of similar people, predictive personas are more focused on detecting the main target customer groups as well as their characteristics by data. The results indicated that traditional quantitative persona and predictive personas are suitable for different scenarios, while traditional quantitative personas are more suitable for providing broadly descriptions on different groups for decision-makers to provide customized services and designs, predictive personas are more for decisions focused on the main target group (for example, the customers expected to purchase). By adding predictive methods to the process of persona creation, the difficulties of the qualitative and traditional quantitative persona creation process are improved and also provided persona creators with a new quantitative persona creation method with a predictive approach.

1. Alkurd, R., Abualhaol, I., & Yanikomeroglu, H. (2020). Big-data-driven and AI-based framework to enable personalization in wireless networks. IEEE Communications Magazine, 58(3), 18-24.
2. An, J., Kwak, H., Jung, S., Salminen, J., Admad, M., & Jansen, B. (2018). Imaginary people representing real numbers: Generating personas from online social media data. ACM Transactions on the Web (TWEB), 12(4), 1-26.
3. Brooks, C., & Greer, J. (2014, March). Explaining predictive models to learning specialists using personas. In Proceedings of the fourth international conference on learning analytics and knowledge (pp. 26-30).
4. Cooper, A. (1999). The inmates are running the asylum. Indianapolis, IA: SAMS. Macmillan.
5. Cooper, A., Reimann, R., & Cronin, D. (2007). About face 3: the essentials of interaction design. John Wiley & Sons.
6. Giacomin, J. (2014). What is human centred design?. The Design Journal, 17(4), 606-623.
7. Hackos, J. T., & Redish, J. (1998). User and task analysis for interface design (Vol. 1). New York: Wiley.
8. Hill, C. G., Haag, M., Oleson, A., Mendez, C., Marsden, N., Sarma, A., & Burnett, M. (2017, May). Gender-Inclusiveness Personas vs. Stereotyping: Can we have it both ways?. In Proceedings of the 2017 chi conference on human factors in computing systems (pp. 6658-6671).
9. Jansen, B. J., Jung, S. G., Salminen, J., Guan, K. W., & Nielsen, L. (2021, January). Strengths and Weaknesses of Persona Creation Methods: Guidelines and Opportunities for Digital Innovations. In Proceedings of the 54th Hawaii International Conference on System Sciences (p. 4971).
10. Jansen, B. J., Salminen, J. O., & Jung, S. G. (2020). Data-driven personas for enhanced user understanding: Combining empathy with rationality for better insights to analytics. Data and Information Management, 4(1), 1-17.
11. Matthews, T., Judge, T., & Whittaker, S. (2012, May). How do designers and user experience professionals actually perceive and use personas?. In Proceedings of the SIGCHI conference on human factors in computing systems (pp. 1219-1228).
12. McGinn, J., & Kotamraju, N. (2008, April). Data-driven persona development. In Proceedings of the SIGCHI conference on human factors in computing systems (pp. 1521-1524).
13. Miaskiewicz, T., & Kozar, K. A. (2011). Personas and user-centered design: How can personas benefit product design processes?. Design studies, 32(5), 417-430.
14. Miaskiewicz, T., & Luxmoore, C. (2017). The use of data-driven personas to facilitate organizational adoption–A case study. The Design Journal, 20(3), 357-374.
15. Miaskiewicz, T., Sumner, T., & Kozar, K. A. (2008, April). A latent semantic analysis methodology for the identification and creation of personas. In Proceedings of the SIGCHI conference on human factors in computing systems (pp. 1501-1510).
16. Mulder, S., & Yaar, Z. (2006). The user is always right: A practical guide to creating and using personas for the web. New Riders.
17. Mulder, S., & Yaar, Z. (2007). Approaches to creating personas. The user is always right: A practical guide to creating and using personas for the web. Berkeley, CA: New Riders, 33-54.
18. Nielsen, L., Nielsen, K. S., Stage, J., & Billestrup, J. (2013, September). Going global with personas. In IFIP Conference on Human-Computer Interaction (pp. 350-357). Springer, Berlin, Heidelberg.
19. Salminen, J., Jansen, B. J., An, J., Kwak, H., & Jung, S. G. (2018). Are personas done? Evaluating their usefulness in the age of digital analytics. Persona Studies, 4(2), 47-65.
20. Salminen, J., Guan, K., Jung, S. G., Chowdhury, S. A., & Jansen, B. J. (2020, April). A literature review of quantitative persona creation. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (pp. 1-14).
21. Salminen, J., Guan, K., Jung, S. G., & Jansen, B. J. (2021). A Survey of 15 Years of Data-Driven Persona Development. International Journal of Human–Computer Interaction, 1-24.
22. Shmueli, G., Bruce, P. C., Yahav, I., Patel, N. R., & Lichtendahl Jr, K. C. (2017). Data mining for business analytics: concepts, techniques, and applications in R. John Wiley & Sons.
23. Su. (2016). Creating Persona with Quantitative Validation：A Data Driven Service Design Methodology. Master dissertation of Institute of Service Science, Tsinghua University, 1-53.
24. Tu, N., He, Q., Zhang, T., Zhang, H., Li, Y., Xu, H., & Xiang, Y. (2010, November). Combine qualitative and quantitative methods to create persona. In 2010 3rd International Conference on Information Management, Innovation Management and Industrial Engineering (Vol. 3, pp. 597-603). IEEE.
25. Zhang, X., Brown, H. F., & Shankar, A. (2016, May). Data-driven personas: Constructing archetypal users with clickstreams and user telemetry. In Proceedings of the 2016 CHI conference on human factors in computing systems (pp. 5350-5359).