Barrett R Anderson’s scientific contributions

What is this page?

This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (4)

Figure 3: This image prompting linkograph contains three refinement webs: one at the beginning, one in the middle, and one at the end. The first web consists of mixed mediumstrength and high-strength links, indicating a greater degree of prompt variation at an earlier level of conceptualization; the other two webs mostly consist of very small permutations of a relatively fixed prompt.
Figure 4: This image prompting linkograph demonstrates a curiosity zigzag, with relatively strong long-range links indicating returns to a central theme and disconnected chunks between these moves indicating periods of exploration.
Figure 5: This image prompting linkograph's "converging zigzag" shape combines a curiosity zigzag with refinement webs: alternation between a central theme of interest and more divergent explorations persists throughout the episode, but previously distinct themes are also brought together into a single image concept on two distinct occasions, each time resulting in a distinctive refinement web.
Figure 6: This image prompting linkograph shows clear semantic divisions between the user's focal themes during several significant temporal "sessions" of prompting. (Vertical dotted lines between moves indicate the user stepping away from prompting for at least 30 minutes.) The first and longest session ends with a clear refinement web.
Figure 7: This image prompting linkograph, on the other hand, shows a user's focal themes persisting across multiple clear temporal divides in prompting activity. The user seems to be engaged in a long-running "project".

+1

Scaling Analysis of Creative Activity Traces via Fuzzy Linkography
  • Conference Paper
  • Full-text available

April 2025

·

6 Reads

Amy Smith

·

Barrett R Anderson

·

Jasmine Tan Otto

·

[...]

·

Download
Figure 3: An example fuzzy linkograph of an open-ended stream-of-consciousness ideation activity. Links between moves are colored according to their strength (with darker lines indicating stronger links). Move text is displayed directly above the move markers. This graph features several critical moves: "hello" and "cat" are forelink critical moves that introduce the themes of greeting and cats respectively; "hello kitty" initially integrates these two themes; and "hello kitty tv show" is a backlink critical move, fully integrating these themes from the session's first half with the "video" theme from its second.
Figure 4: This image prompting linkograph contains three refinement webs: one at the beginning, one in the middle, and one at the end. The first web consists of mixed mediumstrength and high-strength links, indicating a greater degree of prompt variation at an earlier level of conceptualization; the other two webs mostly consist of very small permutations of a relatively fixed prompt.
Figure 5: This image prompting linkograph demonstrates a curiosity zigzag, with relatively strong long-range links indicating returns to a central theme and disconnected chunks between these moves indicating periods of exploration.
Figure 6: This image prompting linkograph's "converging zigzag" shape combines the refinement webs motif with the curiosity zigzag motif: alternation between a central theme of interest and more divergent explorations persists throughout the episode, but previously distinct themes are also brought together into a single image concept on two distinct occasions, each time resulting in a distinctive refinement web.
Figure 10: Three LLM-supported ideation linkographs demonstrating many of the archetypal patterns we observed in ideation traces. Early user ideas (red) are fairly diverse; the LLM (blue) generates large batches of ideas at a time; LLM ideas tend to become more similar to one another as interaction proceeds; and inter-actor links (purple) are dominated by user backlinks to LLM ideas, with users falling into a more curatorial or converging role as LLM output is introduced.
Fuzzy Linkography: Automatic Graphical Summarization of Creative Activity Traces

February 2025

·

39 Reads

Amy Smith

·

Barrett R. Anderson

·

Jasmine Tan Otto

·

[...]

·

Linkography -- the analysis of links between the design moves that make up an episode of creative ideation or design -- can be used for both visual and quantitative assessment of creative activity traces. Traditional linkography, however, is time-consuming, requiring a human coder to manually annotate both the design moves within an episode and the connections between them. As a result, linkography has not yet been much applied at scale. To address this limitation, we introduce fuzzy linkography: a means of automatically constructing a linkograph from a sequence of recorded design moves via a "fuzzy" computational model of semantic similarity, enabling wider deployment and new applications of linkographic techniques. We apply fuzzy linkography to three markedly different kinds of creative activity traces (text-to-image prompting journeys, LLM-supported ideation sessions, and researcher publication histories) and discuss our findings, as well as strengths, limitations, and potential future applications of our approach.

Download

Citations (2)

... Third, a review of the existing literature reveals little direct evidence about the impact of LLMs on employee creativity in real-world organizational settings. Most studies on LLMs and creativity were conducted in online or lab settings, and almost all of them focused on isolated, single tasks (e.g., B. R. Anderson et al., 2024;Boussioux et al., 2024;Z. Chen & Chan, 2024;Doshi & Hauser, 2024;Hitsuwari et al., 2023). ...

Reference:

How and for Whom Using Generative AI Affects Creativity: A Field Experiment
Homogenization Effects of Large Language Models on Human Creative Ideation
Barrett R Anderson

·

Jash Hemant Shah

·

... 2 We introduce ACAI, a multimodal LLM powered ad co-creation tool, designed for novice designers specifically. 3 We provide design recommendations to make AI a better co-creation tool, we recommend contextual intelligence, adaptive interfaces and data management. 4 We illustrate how interface design can lower barriers for novice users and enhance user's brand alignment in GenAI tools, with implications for developing more inclusive AI systems that support novice users in complex creative tasks. ...

Reference:

ACAI for SBOs: AI Co-creation for Advertising and Inspiration for Small Business Owners
Evaluating Creativity Support Tools via Homogenization Analysis
  • Citing Conference Paper

  • May 2024

Barrett R Anderson

·

Jash Hemant Shah

·