The document reports on a study that examined how the inclusion of different types of photos in automatically generated online persona profiles impacts people's perceptions of confusion and informativeness. The study found that including contextual photos increased perceived informativeness while including multiple similar attribute photos increased confusion. The results suggest that including a headshot photo and contextual photos of the same person provides the optimal persona profile design.
This workshop will introduce some of the main principles and techniques of Social Network Analysis (SNA). We will use examples from organizational and social media-based networks to understand concepts such as network density, diameter, centrality measures, community detection algorithms, etc. The session will also introduce Gephi, a popular program for SNA. Gephi is a free and open-source tool that is available for both Mac and PC computers.
By the end of the session, you will develop a general understanding of what SNA is, what research questions it can help you answer, and how it can be applied to your own research. You will also learn how to use Gephi to visualize and examine networks using various layout and community detection algorithms.
Instructor’s Bio: Dr. Anatoliy Gruzd is a Canada Research Chair in Social Media Data Stewardship, Associate Professor at the Ted Rogers School of Management at Ryerson University, and Director of Research at the Social Media Lab. Anatoliy is also a Member of the Royal Society of Canada’s College of New Scholars, Artists and Scientists; a co-editor of a multidisciplinary journal on Big Data and Society; and a founding co-chair of the International Conference on Social Media and Society. His research initiatives explore how social media platforms are changing the ways in which people and organizations communicate, collaborate and disseminate information and how these changes impact the norms and structures of modern society.
Social Network Analysis Introduction including Data Structure Graph overview. Doug Needham
Social Network Analysis Introduction including Data Structure Graph overview. Given in Cincinnati August 18th 2015 as part of the DataSeed Meetup group.
This workshop will introduce some of the main principles and techniques of Social Network Analysis (SNA). We will use examples from organizational and social media-based networks to understand concepts such as network density, diameter, centrality measures, community detection algorithms, etc. The session will also introduce Gephi, a popular program for SNA. Gephi is a free and open-source tool that is available for both Mac and PC computers.
By the end of the session, you will develop a general understanding of what SNA is, what research questions it can help you answer, and how it can be applied to your own research. You will also learn how to use Gephi to visualize and examine networks using various layout and community detection algorithms.
Instructor’s Bio: Dr. Anatoliy Gruzd is a Canada Research Chair in Social Media Data Stewardship, Associate Professor at the Ted Rogers School of Management at Ryerson University, and Director of Research at the Social Media Lab. Anatoliy is also a Member of the Royal Society of Canada’s College of New Scholars, Artists and Scientists; a co-editor of a multidisciplinary journal on Big Data and Society; and a founding co-chair of the International Conference on Social Media and Society. His research initiatives explore how social media platforms are changing the ways in which people and organizations communicate, collaborate and disseminate information and how these changes impact the norms and structures of modern society.
Social Network Analysis Introduction including Data Structure Graph overview. Doug Needham
Social Network Analysis Introduction including Data Structure Graph overview. Given in Cincinnati August 18th 2015 as part of the DataSeed Meetup group.
Contextual Recommendation of Social Updates, a tag-based frameworkAdrien Joly
How to cope with information overload?
In this presentation (and the corresponding paper), we propose a framework to improve the relevance of awareness information about people and subjects, by adapting recommendation techniques to real-time web data, in order to reduce information overload. The novelty of our approach relies on the use of contextual information about people's current activities to rank social updates which they are following on Social Networking Services and other collaborative software. The two hypothesis that we are supporting in this paper are: (i) a social update shared by person X is relevant to another person Y if the current context of Y is similar to X's context at time of sharing; and (ii) in a web-browsing session, a reliable current context of a user can be processed using metadata of web documents accessed by the user. We discuss the validity of these hypothesis by analyzing their results on experimental data.
Presented by Adrien Joly, on the 28/08/2010, at the Active Media Technology (AMT) conference, Toronto, Ontario, Canada.
Detecting Important Life Events on Twitter Using Frequent Semantic and Syntac...COMRADES project
Dickinson, Thomas; Fernandez, Miriam; Thomas, Lisa; Mulholland, Paul; Briggs, Pam and Alani, Harith (2016). Detecting Important Life Events on Twitter Using Frequent Semantic and Syntactic Subgraphs. IADIS International Journal on WWW/Internet, 14(2) pp. 23–37.
http://oro.open.ac.uk/48678/
This Presentation was prepared by Arif Khan
for the Seminar on Introduction to complex systems and social network analysis on 05/03/14 (Wednesday) Organized by BRAC University CSE Department in collaboration with BRAC University Computer Club (BUCC).
Big Data, Small Personas: Research Agenda for Automatic Persona GenerationJoni Salminen
A presentation at ICSEC17. Doha, Qatar. Read more: https://persona.qcri.org
***
Automatic Persona Generation (APG) is a system and methodology developed at Qatar Computing Research Institute, Hamad Bin Khalifa University.
The goal is to give faces to social and online analytics data. Personas can be generated from YouTube, Facebook, and Google Analytics data.
The system can be found at https://persona.qcri.org
Generating Cultural Personas From Social Data - A Perspective of Middle Easte...Joni Salminen
CITE: "Salminen, J., Sercan, Ş., Haewoon, K., Jansen, B. J., An, J., Jung, S., Vieweg, S., Harrell, F. (2017). Generating Cultural Personas from Social Data: A Perspective of Middle Eastern Users. In Proceedings of The Fourth International Symposium on Social Networks Analysis, Management and Security (SNAMS-2017). Prague, Czech Republic, 21–23, August."
Download paper: http://jonisalminen.com/wp-content/uploads/2018/08/Generating-Cultural-Personas-From-Social-Data_SNAMS2017.pdf
***
Automatic Persona Generation (APG) is a system and methodology developed at Qatar Computing Research Institute, Hamad Bin Khalifa University.
The goal is to give faces to social and online analytics data. Personas can be generated from YouTube, Facebook, and Google Analytics data.
The system can be found at https://persona.qcri.org
Lecture series: Using trace data or subjective data, that is the question dur...Bart Rienties
In this lecture series Bart Rienties (Professor of Learning Analytics, head of Academic Professional Development) will discuss how from the safety of your home you could use existing trace data to explore interactions between people (e.g., Twitter data, engagement data in a virtual learning environment, public data sets), and what the affordances and limitations of these trace data might be. Furthermore, he will discuss how other ways of collecting subjective data (e.g., surveys, interviews) might strengthen our understandings of complex interactions between people.
There are no prior requirements to join, and everyone is welcome. For those with a technical background you may enjoy this recent paper in PLOS ONE https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0233977. For those with a non-technical background, you may enjoy this paper https://journals.sfu.ca/flr/index.php/journal/article/view/348
Disinformation challenges tools and techniques to deal or live with itnsarris
Keynote presentation at 1st International Workshop on
Disinformation and Toxic Content Analysis
(DiTox 2023) on the problem of onine disinformation and associated technnologies and policies that help against it. This work was co-funded by the EC in the context of the MedDMO project (contract number 101083756)
This guide was created for NeuroDevNet researchers and trainees (however it could also be useful to practitioners and KT professionals) with an interest in exploring infographics as a KT product. It begins with an evidence-informed introduction followed by an annotated bibliography of web-based resources and ends with appendices of evidence-informed worksheets (see Appendices A-E) created by the KT Core for you to use during the design and creation of your infographic. This guide is intended to provide you with information including: what is an infographic, what are the different types of infographics, what should you consider when planning your infographic, how you can either do it yourself or work with a graphic designer, and a form-fillable tool you can use to help you think through and collate the information you need before sketching a draft of your infographic.
Contextual Recommendation of Social Updates, a tag-based frameworkAdrien Joly
How to cope with information overload?
In this presentation (and the corresponding paper), we propose a framework to improve the relevance of awareness information about people and subjects, by adapting recommendation techniques to real-time web data, in order to reduce information overload. The novelty of our approach relies on the use of contextual information about people's current activities to rank social updates which they are following on Social Networking Services and other collaborative software. The two hypothesis that we are supporting in this paper are: (i) a social update shared by person X is relevant to another person Y if the current context of Y is similar to X's context at time of sharing; and (ii) in a web-browsing session, a reliable current context of a user can be processed using metadata of web documents accessed by the user. We discuss the validity of these hypothesis by analyzing their results on experimental data.
Presented by Adrien Joly, on the 28/08/2010, at the Active Media Technology (AMT) conference, Toronto, Ontario, Canada.
Detecting Important Life Events on Twitter Using Frequent Semantic and Syntac...COMRADES project
Dickinson, Thomas; Fernandez, Miriam; Thomas, Lisa; Mulholland, Paul; Briggs, Pam and Alani, Harith (2016). Detecting Important Life Events on Twitter Using Frequent Semantic and Syntactic Subgraphs. IADIS International Journal on WWW/Internet, 14(2) pp. 23–37.
http://oro.open.ac.uk/48678/
This Presentation was prepared by Arif Khan
for the Seminar on Introduction to complex systems and social network analysis on 05/03/14 (Wednesday) Organized by BRAC University CSE Department in collaboration with BRAC University Computer Club (BUCC).
Big Data, Small Personas: Research Agenda for Automatic Persona GenerationJoni Salminen
A presentation at ICSEC17. Doha, Qatar. Read more: https://persona.qcri.org
***
Automatic Persona Generation (APG) is a system and methodology developed at Qatar Computing Research Institute, Hamad Bin Khalifa University.
The goal is to give faces to social and online analytics data. Personas can be generated from YouTube, Facebook, and Google Analytics data.
The system can be found at https://persona.qcri.org
Generating Cultural Personas From Social Data - A Perspective of Middle Easte...Joni Salminen
CITE: "Salminen, J., Sercan, Ş., Haewoon, K., Jansen, B. J., An, J., Jung, S., Vieweg, S., Harrell, F. (2017). Generating Cultural Personas from Social Data: A Perspective of Middle Eastern Users. In Proceedings of The Fourth International Symposium on Social Networks Analysis, Management and Security (SNAMS-2017). Prague, Czech Republic, 21–23, August."
Download paper: http://jonisalminen.com/wp-content/uploads/2018/08/Generating-Cultural-Personas-From-Social-Data_SNAMS2017.pdf
***
Automatic Persona Generation (APG) is a system and methodology developed at Qatar Computing Research Institute, Hamad Bin Khalifa University.
The goal is to give faces to social and online analytics data. Personas can be generated from YouTube, Facebook, and Google Analytics data.
The system can be found at https://persona.qcri.org
Lecture series: Using trace data or subjective data, that is the question dur...Bart Rienties
In this lecture series Bart Rienties (Professor of Learning Analytics, head of Academic Professional Development) will discuss how from the safety of your home you could use existing trace data to explore interactions between people (e.g., Twitter data, engagement data in a virtual learning environment, public data sets), and what the affordances and limitations of these trace data might be. Furthermore, he will discuss how other ways of collecting subjective data (e.g., surveys, interviews) might strengthen our understandings of complex interactions between people.
There are no prior requirements to join, and everyone is welcome. For those with a technical background you may enjoy this recent paper in PLOS ONE https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0233977. For those with a non-technical background, you may enjoy this paper https://journals.sfu.ca/flr/index.php/journal/article/view/348
Disinformation challenges tools and techniques to deal or live with itnsarris
Keynote presentation at 1st International Workshop on
Disinformation and Toxic Content Analysis
(DiTox 2023) on the problem of onine disinformation and associated technnologies and policies that help against it. This work was co-funded by the EC in the context of the MedDMO project (contract number 101083756)
This guide was created for NeuroDevNet researchers and trainees (however it could also be useful to practitioners and KT professionals) with an interest in exploring infographics as a KT product. It begins with an evidence-informed introduction followed by an annotated bibliography of web-based resources and ends with appendices of evidence-informed worksheets (see Appendices A-E) created by the KT Core for you to use during the design and creation of your infographic. This guide is intended to provide you with information including: what is an infographic, what are the different types of infographics, what should you consider when planning your infographic, how you can either do it yourself or work with a graphic designer, and a form-fillable tool you can use to help you think through and collate the information you need before sketching a draft of your infographic.
Picturing the Social: Talk for Transforming Digital Methods Winter SchoolFarida Vis
This talk highlights the work of the Visual Social Media Lab and the Picturing the Social project. It summarises the key research questions and aims of the project. It highlights the value of interdisciplinarity and working closely with industry in this area. It also focuses on the way in which me might study different types of structures involved in the circulation and the scopic regimes that make social media images more or less visible. It also tries to unpack how we can start to think about APIs as 'method' and looks at the different ways in which we can get access to different kinds of social media image data. Both through public ('free') APIs and ('pay for') firehose data.
Explainable AI is not yet Understandable AIepsilon_tud
Keynote of Dr. Nava Tintarev at RCIS'2020. Decision-making at individual, business, and societal levels is influenced by online content. Filtering and ranking algorithms such as those used in recommender systems are used to support these decisions. However, it is often not clear to a user whether the advice given is suitable to be followed, e.g., whether it is correct, whether the right information was taken into account, or if the user’s best interests were taken into consideration. In other words, there is a large mismatch between the representation of the advice by the system versus the representation assumed by its users. This talk addresses why we (might) want to develop advice-giving systems that can explain themselves, and how we can assess whether we are successful in this endeavor. This talk will also describe some of the state-of-the-art in explanations in a number of domains (music, tweets, and news articles) that help link the mental models of systems and people. However, it is not enough to generate rich and complex explanations; more is required in order to understand and be understood. This entails among other factors decisions around which information to select to show to people, and how to present that information, often depending on the target users and contextual factors
Similar to Is More Better?: Impact of Multiple Photos on Perception of Persona Profiles (20)
User Studies for APG: How to support system development with user feedback?Joni Salminen
Presentation at QCRI's Science Monday of the Social Computing group. January 14, 2019. Doha, Qatar. Access the Automatic Persona Generation system: https://persona.qcri.org
Combining Behaviors and Demographics to Segment Online Audiences:Experiments ...Joni Salminen
Link to article: https://www.springerprofessional.de/en/combining-behaviors-and-demographics-to-segment-online-audiences/16204306
CITE: Jansen, Bernard J., Jung, S., Salminen, J., An, J. and Kwak, H. (2018), “Combining Behaviors and Demographics to Segment Online Audiences: Experiments with a YouTube Channel”, Proceedings of the 5th International Conference of Internet Science (INSCI 2018), Springer, St. Petersburg, Russia.
Link to Automatic Persona Generation: https://persona.qcri.org
Research Roadmap for Automatic Persona Generation (2018)Joni Salminen
Automatic Persona Generation (APG) is a system and methodology developed at Qatar Computing Research Institute, Hamad Bin Khalifa University. Read more: https://persona.qcri.org
The goal of Automatic Persona Generation is to give faces to social and online analytics data. Personas can be generated from YouTube, Facebook, and Google Analytics data.
If you are interested in research collaboration, please contact Professor Jim Jansen at bjansen@hbku.edu.qa
To Use Branded Keywords or Not? Rationale of Professional Search-engine Marke...Joni Salminen
CITE: "Lyytikkä, J., Salminen, J., & Jansen, B. J. (2018). To Use Branded Keywords or Not? Rationale of Professional Search-engine Marketers for Brand Bidding Strategy. Presented at the 13th Global Brand Conference, Northumbria University, UK, 2–4 May."
Download paper: http://jonisalminen.com/wp-content/uploads/2018/08/To-use-branded-keywords-or-not-Rationale-of-professional-search-engine-marketers-for-brand-bidding-strategy.pdf
Determining Online Brand Reputation with Machine Learning from Social Media M...Joni Salminen
CITE: "Rantanen, A., Salminen, J., & Jansen, B. J. (2018). Determining Online Brand Reputation with Machine Learning from Social Media Mentions: A Study in the Banking Context. Presented at the 13th Global Brand Conference, Northumbria University, UK, 2–4 May."
Anatomy of Online Hate: Developing a Taxonomy and Machine Learning Models for...Joni Salminen
CITE: "Salminen, J., Almerekhi, H., Milenković, M., Jung, S., An, J., Kwak, H., & Jansen, B. J. (2018). Anatomy of Online Hate: Developing a Taxonomy and Machine Learning Models for Identifying and Classifying Hate in Online News Media. In Proceedings of the International AAAI Conference on Web and Social Media (ICWSM 2018), San Francisco, California, USA, 25–28 June."
Download paper: http://jonisalminen.com/wp-content/uploads/2018/08/Anatomy-of-hate_aaai18_ICWSM18_submit_final_camera.pdf
OSS-EBM: Open Source Software Entrepreneurial Business ModellingJoni Salminen
CITE: Teixeira, J., & Salminen, J. (2014). Open-Source Software Entrepreneurial Business Modelling. In L. Corral, A. Sillitti, G. Succi, J. Vlasenko, & A. I. Wasserman (Eds.), Open Source Software: Mobile Open Source Technologies (pp. 80–82). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-55128-4_10
Gender effect on e-commerce sales of experience gifts: Preliminary empirical ...Joni Salminen
CITE: "Salminen, J., Seitz, S., Jansen, B. J., & Salenius, T. (2017). Gender Effect on E-Commerce Sales of Experience Gifts: Preliminary Empirical Findings. In Proceedings of International Conference on Electronic Business (ICEB 2017). Dubai, 4–8 December."
We analyze purchase data from 493 customers of an e-commerce store selling experience gifts to find how gender correlates with average purchase value, category of purchased products, and the use of discount codes. We find no significant differences for average purchase value or category of purchased products, but according to the data, women are more likely to use discount codes than are males. Ideas for further research concerning the gender effect on online shopping behavior are discussed.
Link to full paper: https://www.researchgate.net/publication/321586760_Gender_effect_on_e-commerce_sales_of_experience_gifts_Preliminary_empirical_findings
Keywords: e-commerce; online consumer behavior; online purchase behavior; online shopping behavior; gender
Why do startups avoid difficult problems?Joni Salminen
CITE: "Salminen, J. (2013) Why avoid difficult problems? Exploring the avoidance behavior within startup motive. Proceedings of LCBR European Marketing Conference, August 15–16, 2013, Frankfurt."
Download paper: http://jonisalminen.com/wp-content/uploads/2018/08/why-founders-avoid-difficult-problems.pdf
Social Espionage: Drawing Benefit from Competitors’ Social Media PresenceJoni Salminen
CITE: "Salminen, J., & Degbey, W. (2011). Social Espionage – Drawing Benefit from Competitors’ Social Media Presence. In Proceedings of High Technology Small Firms Conference, Manchester, UK, 10–11 June."
Who does what in marketing? Toward an understanding of marketer–machine inter...Joni Salminen
CITE: "Salminen, J., Sarlin, P., Olkkonen, R. & Jansen, B. (2017). Who Does What in Marketing? Toward an Understanding of Marketer–machine Interaction. The International AAAI Conference on Web and Social Media (ICWSM2017) Workshop: Studying User Perceptions and Experiences with Algorithms, Montreal, Canada, 16–18 May."
Download paper: http://jonisalminen.com/wp-content/uploads/2018/08/who-does-what-in-marketing_ICWSM17.pdf
Today the Social Computing group at Qatar Computing Research Institute had the pleasure to listen to the presentation of Luis Fernandez-Luque about social media marketing for researchers. Luis talked about how to promote your publications and personal brand, as well as how to reach the right people on social media with your research.
In this presentation, I'll summarize some points of his presentation (if you want the full thing, you need to ask him :), and reflect them on my own experiences as a digital marketer.
Between Filth and Fortune- Urban Cattle Foraging Realities by Devi S Nair, An...Mansi Shah
This study examines cattle rearing in urban and rural settings, focusing on milk production and consumption. By exploring a case in Ahmedabad, it highlights the challenges and processes in dairy farming across different environments, emphasising the need for sustainable practices and the essential role of milk in daily consumption.
Expert Accessory Dwelling Unit (ADU) Drafting ServicesResDraft
Whether you’re looking to create a guest house, a rental unit, or a private retreat, our experienced team will design a space that complements your existing home and maximizes your investment. We provide personalized, comprehensive expert accessory dwelling unit (ADU)drafting solutions tailored to your needs, ensuring a seamless process from concept to completion.
White wonder, Work developed by Eva TschoppMansi Shah
White Wonder by Eva Tschopp
A tale about our culture around the use of fertilizers and pesticides visiting small farms around Ahmedabad in Matar and Shilaj.
Hello everyone! I am thrilled to present my latest portfolio on LinkedIn, marking the culmination of my architectural journey thus far. Over the span of five years, I've been fortunate to acquire a wealth of knowledge under the guidance of esteemed professors and industry mentors. From rigorous academic pursuits to practical engagements, each experience has contributed to my growth and refinement as an architecture student. This portfolio not only showcases my projects but also underscores my attention to detail and to innovative architecture as a profession.
Dive into the innovative world of smart garages with our insightful presentation, "Exploring the Future of Smart Garages." This comprehensive guide covers the latest advancements in garage technology, including automated systems, smart security features, energy efficiency solutions, and seamless integration with smart home ecosystems. Learn how these technologies are transforming traditional garages into high-tech, efficient spaces that enhance convenience, safety, and sustainability.
Ideal for homeowners, tech enthusiasts, and industry professionals, this presentation provides valuable insights into the trends, benefits, and future developments in smart garage technology. Stay ahead of the curve with our expert analysis and practical tips on implementing smart garage solutions.
You could be a professional graphic designer and still make mistakes. There is always the possibility of human error. On the other hand if you’re not a designer, the chances of making some common graphic design mistakes are even higher. Because you don’t know what you don’t know. That’s where this blog comes in. To make your job easier and help you create better designs, we have put together a list of common graphic design mistakes that you need to avoid.
Is More Better?: Impact of Multiple Photos on Perception of Persona Profiles
1. “Is More Better?”: Impact of
Multiple Photos
on Perception of Persona Profiles
(+Intro to Automatic Persona Generation)
News & Social Media Analytics Team
Social Computing Group
Qatar Computing Research Institute
Hamad Bin Khalifa University
2. The APG Team
Dr. Jisun An
Scientist
Dr. Haewoon Kwak
Scientist
Prof. Jim Jansen
Leader
Soon-Gyo Jung
Engineer
Dr. Joni Salminen
Post-doctoral researcher
+Dr. Lene
Nielsen
IT University
Copenhagen
4. What is a persona?
• A ‘persona’ is a fictive person describing an
important user group.
• Simplifies numerical data into an easy format:
another human being
• Personas help communicate numbers in the
organization, so that decisions can be made
keeping the end customer in mind.
5. Which one do you prefer?
vs.
“Personas give faces to data.”
A lot of numbers… Austin, a 35-year-old diving
enthusiast.
6. What is Automatic Persona
Generation (APG)?
A methodology and a system for automatically
creating personas from online analytics data.
Current status:
a. processing hundreds of millions of user interactions from
YouTube, Facebook and Google Analytics.
b. stable and robust system using Flask framework, PostgreSQL
database, and Pandas/scikit-learn data analysis library
c. deployed with Al Jazeera English, AJ+ Arabic, AJ+ San
Francisco, Qatar Foundation, and Qatar Airways for actual
use.
7. Why automate persona creation?
Personas are usually created with manual methods, such as interviews
and ethnography. Manual methods are expensive, do not cover many
users, and the personas can become outdated. Therefore, even after
creation, organizations cannot be certain the personas accurately
represent their true user base at a given time.
APG can help:
1. Real behavioral data from online analytics and social media
platforms
2. Faster creation time, from access to ready in a matter of hours
3. Updates each month to reflect changes of user preferences
The mission: Better personas better decisions better results.
11. 3.
Finally, show the individual personas.
A: Picture
B: Name, age, gender,
location
C: Text description
D: Topics of interest (most
and least)
E: Descriptive quotes
F: Content the persona is
most interested in
(G: Share of this persona of
the overall audience)
12. Of course, more is happening
in the background…
Configuration
Collection
Generation
A matrix of
content interaction patterns
Automatically generated
personas
Collection/Generation/API
information
13. Of course, more is happening
in the background…
Configuration
Collection
Generation
A matrix of
content interaction patterns
Automatically generated
personas
Collection/Generation/API
information
An, J., Kwak, H., & Jansen, B. J. (2017). Personas for
Content Creators via Decomposed Aggregate Audience
Statistics. In Proceedings of Advances in Social Network
Analysis and Mining (ASONAM 2017). Sydney, Australia.
Read:
14. Information architecture:
How to choose the correct
information elements and
layout for a given user,
context or industry?
Comments:
How to find representative,
contextually relevant,
and non-distracting
comments describing the
persona.
Evaluation: How to ensure
personas are complete,
clear, consistent and
credible? How to measure
usefulness of personas for
individuals and
organizations?
Topics of interest:
How to describe the persona’s
interests across platforms and
contexts?
Image: How to generate
and choose correct
persona profile
pictures?
Temporal analysis:
How to analyze change
and stability of
personas in time?
Attributes: How to infer attributes,
such as psychographics, needs and
wants, political orientation and brand
affinities.
Finding better ways to automatically process and choose useful
information from vast amounts of online data. ”Giving faces to data”
Description: How to
describe the persona in a
fluent and useful way?
15. Information architecture:
How to choose the correct
information elements and
layout for a given user,
context or industry?
Comments:
How to find representative,
contextually relevant,
and non-distracting
comments describing the
persona.
Evaluation: How to ensure
personas are complete,
clear, consistent and
credible? How to measure
usefulness of personas for
individuals and
organizations?
Topics of interest:
How to describe the persona’s
interests across platforms and
contexts?
Image: How to generate
and choose correct
persona profile
pictures?
Temporal analysis:
How to analyze change
and stability of
personas in time?
Attributes: How to infer attributes,
such as psychographics, needs and
wants, political orientation and brand
affinities.
Finding better ways to automatically process and choose useful
information from vast amounts of online data. ”Giving faces to data”
Description: How to
describe the persona in a
fluent and useful way?
16. Research question and
hypotheses
• H1a and b: Adding [a: contextual, b: attribute-similar]
images increases the perceived confusion relative to a
headshot image.
• H2a and b: Adding [a: contextual, b: attribute-similar]
images increases the perceived informativeness relative to a
headshot image.
• H3: Image changes to the persona profile that cause
confusion result in lower informativeness.
• RQ1: Do the images incite associations and cultural
assumptions on top of the written information?
17. • Did a user study to see
how people interacted
with personas
• Found that quotes and
images cause judgment
toward the persona
The new goal: Find out if
toxic comments steer
attention away from other
information (and develop
advanced filtering)
Treatments:
20. “You are creating a news video about
[International Affairs / Refugees / Israel-
Palestine]. You want to get some insights
on how to pitch your story. As part of
your investigation, you view the following
persona page, looking for content on the
page to see if it can help you pitch your
story. Be sure and TALK ALOUD, saying
what you are looking at and why. Use the
mouse as you normally would. Click as
you normally would but the links are
disabled, just let the moderator know why
you are clicking on some portion of the
page. Once you are finished, let the
moderator know.”
Operationalization:
21. “[I’m] confused about characteristics of this
person.” (P26, T2) Confused: general
“quotes are not clear, from who they are.”
(P26, T3) Confused: quotes
“I’m a little confused, all different women”
(P14, T3) Confused: photos
If a Participant-Treatment involved cues of
confusion (or informativeness), it was coded as
Confusion = 1 (Informativeness = 1), otherwise 0.
[1] T. Tenbrink, “Cognitive Discourse Analysis: accessing cognitive
representations and processes through language data,” Language and
Cognition, vol. 7, pp. 98–137, 2014.
Cognitive Discourse
Analysis [1]:
22. “[I’m] confused about characteristics of this
person.” (P26, T2) Confused: general
“quotes are not clear, from who they are.”
(P26, T3) Confused: quotes
“I’m a little confused, all different women”
(P14, T3) Confused: photos
If a Participant-Treatment involved cues of
confusion (or informativeness), it was coded as
Confusion = 1 (Informativeness = 1), otherwise 0.
[1] T. Tenbrink, “Cognitive Discourse Analysis: accessing cognitive
representations and processes through language data,” Language and
Cognition, vol. 7, pp. 98–137, 2014.
Cognitive Discourse
Analysis [1]:
Fleiss’ kappa = 0.71
Inter-coder agreement
Confusion = A cognitive state of
the user where user verbally
expresses disorientation.
Informativeness = A cognitive
state of the user in which the user
verbally expresses a high degree
of details of the persona.
Concepts
23. We found a significant difference of confusion between
T1 and T3 (p=0.001). In other words, showing the
multiple attribute-similar photos has a statistically
significant impact on confusion. Thus, H1b is supported,
but H1a is not: adding attribute-similar images increases
the perceived confusion relative to a headshot image but
adding contextual images does not increase confusion.
Findings:
We found a significant difference of informativeness
between T1 and T2 (p=0.001) and T1 and T3 (p=0.048),
indicating that the persona profile with one headshot
image differs from those with contextual images by
informativeness. H2a and H2b are supported: adding
contextual images increases the perceived
informativeness relative to a headshot image as does
adding attribute-similar images. However, there is no
statistically significant difference between T2 and T3.
H1a: Not supported
H1b: Supported
H2a: Supported
H2b: Supported
24. We found a significant difference of confusion between
T1 and T3 (p=0.001). In other words, showing the
multiple attribute-similar photos has a statistically
significant impact on confusion. Thus, H1b is supported,
but H1a is not: adding attribute-similar images increases
the perceived confusion relative to a headshot image but
adding contextual images does not increase confusion.
Findings:
We found a significant difference of informativeness
between T1 and T2 (p=0.001) and T1 and T3 (p=0.048),
indicating that the persona profile with one headshot
image differs from those with contextual images by
informativeness. H2a and H2b are supported: adding
contextual images increases the perceived
informativeness relative to a headshot image as does
adding attribute-similar images. However, there is no
statistically significant difference between T2 and T3.
H1a: Not supported
H1b: Supported
H2a: Supported
H2b: Supported
25. We found that T1 has the highest
number of participants with ‘No
confusion & No informativeness’, T2
has the highest number of
participants with ‘No confusion &
informativeness’, and T3 has the
highest number of participants with
‘Confusion & No informativeness’.
Following these frequencies, T2 can
be interpreted as the optimal design
among the ones tested (i.e., persona
description with a headshot and
contextual photos of the same
person than in the headshot).
Design implications:
26. “I would say her search and her interests are
based on who she is and how she was raised
by previous generations, what they educated
her in of their growing up. This has obviously
peaked her interest in race stories; she is
into black American politics because we are
seeing how politics are going in U.S. and both
of those facets feed into human stories. So,
she is an empathetic culturally aware person
that is aware of her own identity who she is
in the general scheme of things.” (P11,
version A)
People are making up stories.
Pictures have an enforcing effect to
sensemaking: participants mention
more often user features that would
not be detected from text only
(black, young).
Remember, we choose the ethnicity
of the persona. Design power !!!
Qualitative insights:
27. Qualitative insights: “from US, living a good life, can’t
relate to refugees -- people who have
rough life.” (version B: three images
of happiness)
“[the persona’s] most striking
features are: cynical, negative, short
attention span.”
“[the persona is] into refugee issues,
or so she says. The quotes counter
that; she’s not interested based on
them.”
People are judging the
personas based on chosen
pictures and quotes.
Design power !!!
28. Qualitative insights: “from US, living a good life, can’t
relate to refugees -- people who have
rough life.” (version B: three images
of happiness)
“[the persona’s] most striking
features are: cynical, negative, short
attention span.”
“[the persona is] into refugee issues,
or so she says. The quotes counter
that; she’s not interested based on
them.”
People are judging the
personas based on chosen
pictures and quotes.
Design power !!!
29. Qualitative insights: “from US, living a good life, can’t
relate to refugees -- people who have
rough life.” (version B: three images
of happiness)
“[the persona’s] most striking
features are: cynical, negative, short
attention span.”
“[the persona is] into refugee issues,
or so she says. The quotes counter
that; she’s not interested based on
them.”
People are judging the
personas based on chosen
pictures and quotes.
Design power !!!
30. Background information that helps the user
understand the persona: education, job, where in
the U.S. she lives, etc.
Peripheral information that helps when
producing content: when she reads, if she watches
videos partly or wholly, her rate of engaging with
the content on social media, etc.
Information about the data sources, explaining
sources, definitions, and representativeness
Since automatically generated personas do not
currently include this level of information, the
informants, in some cases, are left either lacking
the details on persona attributes, or ‘filling in the
gaps’ based on their own experiences, biases, and
stereotypes that they project on the photos.
Information needs are
instrumental to creating
richer persona profiles.
Design implications:
31. Background information that helps the user
understand the persona: education, job, where in
the U.S. she lives, etc.
Peripheral information that helps when
producing content: when she reads, if she watches
videos partly or wholly, her rate of engaging with
the content on social media, etc.
Information about the data sources, explaining
sources, definitions, and representativeness
Since automatically generated personas do not
currently include this level of information, the
informants, in some cases, are left either lacking
the details on persona attributes, or ‘filling in the
gaps’ based on their own experiences, biases, and
stereotypes that they project on the photos.
Information needs are
instrumental to creating
richer persona profiles.
Design implications:
32. Persona Crowd Experiments that involve
manipulations to persona profiles and examine the
effects on persona perceptions
User Study 2.0 that deals with multimodal data
(eye-tracking, mouse-tracking, EEG, emotion
tracking, voice recording).
Persona Perception Scale, quantifying the
measurement of perceptions of end users of
personas.
If you find these topics interesting, collaborate
with us! Just send me an email at
jsalminen@hbku.edu.qa (Joni Salminen)
Future research:
33. Persona Crowd Experiments that involve
manipulations to persona profiles and examine the
effects on persona perceptions
User Study 2.0 that deals with multimodal data
(eye-tracking, mouse-tracking, EEG, emotion
tracking, voice recording).
Persona Perception Scale, quantifying the
measurement of perceptions of end users of
personas.
If you find these topics interesting, collaborate
with us! Just send me an email at
jsalminen@hbku.edu.qa (Joni Salminen)
Future research:
34. Thanks!
Salminen, J., Nielsen, L., Jung, S.-G., An, J., Kwak, H.,
& Jansen, B. J. (2018). “Is More Better?”: Impact of
Multiple Photos on Perception of Persona Profiles. In
Proceedings of ACM CHI Conference on Human
Factors in Computing Systems (CHI2018). Montréal,
Canada.