=Paper=
{{Paper
|id=Vol-3712/paper5
|storemode=property
|title=Generative Primes and Summaries for Reading in Distractive Environments
|pdfUrl=https://ceur-ws.org/Vol-3712/paper5.pdf
|volume=Vol-3712
|authors=Tilman Dingler,Namrata Srivastava,Shaun Wallace
|dblpUrl=https://dblp.org/rec/conf/mum/DinglerSW23
}}
==Generative Primes and Summaries for Reading in Distractive Environments==
https://ceur-ws.org/Vol-3712/paper5.pdf
Generative Primes and Summaries for Reading in
Distractive Environments
Tilman Dingler1 , Namrata Srivastava2 and Shaun Wallace3
1
Delft University of Technology, Netherlands
2
Monash University, Australia
3
University of Rhode Island, USA
Abstract
The proliferation of mobile phones has made reading on these devices increasingly common, but it has
also exposed readers to a plethora of distractions, both internal (e.g., incoming SMS or phone calls) and
external (e.g., navigating a footpath). Resuming a reading task after a distraction can be a daunting
and time-consuming endeavour. To address this challenge, our research explores using automated text
summaries and visualizations, powered by Large Language Models (LLMs), to aid readers in distractive
environments. These summaries and visualizations can be triggered both before and after distractions
occur, offering a flexible approach to mitigating interruptions. This paper delves into the concept of
generative primes - text summaries and visualizations presented before a distraction happens - and post
hoc text summaries and visualizations. We evaluate the effectiveness of these approaches in terms of their
ability to faithfully represent the content and how effectively they assist readers in comprehending and
recalling the text. Large Language Models open up new possibilities for developing reading interfaces
that empower readers to seamlessly handle distractions and effortlessly pick up where they left off in their
reading sessions as well as provide opportunities for memory consolidation. Our research sheds light
on how these advances can positively impact the reading experience in today’s increasingly distractive
digital landscape.
Keywords
Reading interfaces, attention management, priming, generative AI.
1. Introduction
The advent of mobile technology has transformed the way we engage with written content.
From e-books and digital articles to social media feeds and messaging apps, our mobile devices
have become the primary medium through which we access and consume written information.
While this shift offers unprecedented convenience and accessibility, it has also introduced new
challenges, particularly in environments where distractions abound [1, 2]. Reading on mobile
phones in such distractive contexts presents a unique conundrum, as the constant influx of
notifications, both internal (e.g., incoming SMS or phone calls) and external (e.g., navigating a
busy street), disrupts the immersive reading experience. These distractions not only hinder the
enjoyment of reading but also harm comprehension and memory retention [3, 4].
MuM’23 Workshop on Interruptions and Attention Management: Exploring the Potential of Generative AI
Envelope-Open t.dingler@tudelft.nl (T. Dingler); namrata.srivastava@monash.edu (N. Srivastava); shaun.wallace@uri.edu
(S. Wallace)
Orcid 0000-0001-6180-7033 (T. Dingler); 0000-0003-4194-318X (N. Srivastava); 0000-0001-5297-1659 (S. Wallace)
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
Option 1: Text Summary Option 2: Image Summary Option 3: Mindmap Summary
Figure 1: An example of three AI-generated priming representations used in our study for mitigating
the effects of reading interruption - textual (in the form of text summaries), visual (in the form of images),
and conceptual (in the form of mind-maps).
As reading is increasingly becoming an activity that is performed on the go, it is vital to
address the impact of distractive environments. Recent research highlights the prevalence of
mobile phone usage for media consumption. According to a report by the World Economic
Forum, people now spend over four hours a day reading, listening, and watching on their mobile
phones [5]. This shift in media consumption, including reading habits, raises questions about
the quality of information intake and the ability to maintain focus amid the constant barrage of
distractions.
The interruptions experienced while reading on mobile devices are twofold. First, there are
internal disruptions, such as incoming text messages, phone calls, or app notifications, which
divert the reader’s attention away from the text [1]. Second, external factors, like navigating a
crowded sidewalk, further compound the challenge of maintaining reading continuity [1]. As a
result, readers often find themselves in the unenviable position of having to navigate a maze
of distractions before they can resume their reading [6]. This, in turn, can lead to frustration,
diminished comprehension, and difficulties in recalling information from the text.
At the heart of interruptions lies the concept of switching costs, i.e., the time and mental
resources it takes to shift focus from one activity to another (and potentially back). Workers have
been shown to struggle to shift and resume their tasks after interruptions [7]. One potential
solution to this dilemma lies in integrating cues for task resumption [8]. In our work, we
investigate in which ways keywords, text summaries, and visualizations can be used as cues to
allow readers to resume reading activities and consolidate comprehension and memory. Here,
we make use of the so-called priming effect, i.e., an effect from psychology where exposure
to one stimulus influences the response to a subsequent stimulus. In essence, we investigate
how textual and visual previews of passages affect reading comprehension [9] and help readers
bridge interruptions [10].
In recent studies, we have further focused on whether such text primes should be administered
after an interruption occurred or beforehand (e.g., by delaying an incoming call). The design of
these cues, however, has so far been labour-intensive as interruptions can occur at arbitrary
points during text reading and cues hence need to be generated for any number of text passages.
In our era, where Large Language Models (LLMs) have become increasingly sophisticated,
these summaries and visualizations can be created in an automated fashion, however, and
customized to the reader’s preferences. LLMs have significantly advanced the field of Natural
Language Processing (NLP) and have been instrumental in tasks like text summarization,
language translation, and information retrieval [11, 12]. GPT-3, for example, has demonstrated
remarkable capabilities in understanding and generating human-like text, sparking interest in
leveraging such models to enhance the reading experience [Brown et al., 2020]. These LLMs
can be harnessed to power a new generation of reading interfaces that mitigate the negative
effects of distractions. By providing readers with informative summaries and visualizations,
these interfaces have the potential to facilitate smoother transitions between reading and
interruptions.
This position paper delves into the concept of generative primes, i.e., content cues in the
form of text, graphical and image visualizations that help readers preview and review text
passages and mitigate the effects of interruptions. We investigate the benefits of presenting
such primes before a distraction occurs and explore post-hoc summaries and visualizations,
which help readers re-orient themselves after being interrupted. Our research evaluates how
well these generative primes represent the content and how effectively they assist readers in
comprehending and recalling the text.
Our research aims to contribute to a deeper understanding of how generative primes, empow-
ered by LLMs, can revolutionize how we read in distractive environments. By offering insights
into their effectiveness and applications, we hope to pave the way for a more seamless and
enjoyable reading experience in the era of constant digital distractions.
2. The Concept of Generative Primes
The concept of ”generative primes” represents an approach to address the challenges of reading in
distractive environments. Generative primes are cues that provide readers with text summaries
and visualizations either before a distraction occurs or after it has disrupted their reading. These
elements act as cognitive aids, preparing the reader for the upcoming content or assisting in
the resumption of the reading task after an interruption. By combining textual summaries
and visualizations, generative primes create a holistic reading experience that can enhance
comprehension, recall, and engagement.
In the past, we utilized the priming effect to facilitate text comprehension [13] and tested
different visualizations, including text highlights, structured mind maps, and image galleries [9].
Primes had to be manually crafted, which limited this type of research to controlled lab studies
with selected texts. by leveraging the power of LLMs to generate automated summaries and
images from text, these generative primes can finally be scaled and deployed in the wild.
To implement generative primes, Large Language Models (LLMs) like ChatGPT are invaluable
for generating text summaries. ChatGPT is trained to understand and generate human-like
text, making it ideal for creating concise, coherent, and informative textual overviews of longer
passages. These summaries can serve as previews or reorientation tools, ensuring that readers
stay connected to the content despite distractions.
Visualizations are essential components of generative primes that complement text summaries.
Software tools like Midjourney and DALL-E have been revolutionary in this regard. Midjourney
can create visualizations through image stories, distilling complex textual information into
visually appealing and easily comprehensible narratives. Meanwhile, DALL-E can generate in-
novative visualizations, such as mind maps that visually represent the structure and connections
within the text.
The synergy of text summaries from LLMs like ChatGPT and visualizations from software like
Midjourney and DALL-E enables the creation of generative primes that cater to diverse learning
and reading styles. These primes hold the potential to revolutionize the way we interact with
written content in distractive environments, making the reading experience more engaging,
informative, and resilient to interruptions.
3. Research Plan and Outlook
In our recent work, we explored the impact of interruptions on reading comprehension and
how these effects can be mitigated using reviews (summaries of already read content) and
previews (summaries of upcoming content) [10]. We conducted a series of pilot studies involving
participants reading on mobile devices and being interrupted by various tasks. The studies
aimed to determine whether presenting these summaries before or after interruptions could aid
in re-engaging with the reading material and improving comprehension.
We found that previews shown after interruptions significantly enhanced reading compre-
hension compared to not showing any summaries. Reviews also helped, but to a lesser extent
than previews. The effectiveness of these priming cues varied based on the type of reading
material and the timing of the cue presentation.
Despite the effectiveness of previews in aiding comprehension, most participants expressed a
preference for reviews. They found reviews more helpful in summarizing key points and aiding
in answering comprehension questions. A significant number of participants (79.3%), however,
preferred having some form of summary (either review or preview) compared to none.
These studies suggest that smart reading applications could incorporate text summaries,
especially previews after interruptions, to facilitate better comprehension and re-engagement
with reading tasks. Hence, we are now in the process of utilizing LLMs to generate text
summaries and visualizations on the fly to create text primes. Figure 2 shows the process of
creating three types of primes—text summary, image story, and a mindmap—from prompting to
Please write a brief and concise summary of the fol-
In the adventurous short story "The Cam-
Text-Priming lowing article. It should provide an overview of the
main points, key arguments, and findings, but should
el's Back," young Chan defies her parents'
instructions not to ride the family motorcy-
Generation not exceed 100 words. Ensure the summary accurate-
ly reflects the essence of the article, giving the reader
cle unsupervised. As her family leaves for
the evening, Chan yields to temptation,
an understanding of the content without having to taking her bike out for a thrilling ride
read the entire piece. Remember, this summary across the family's field. Pushing her limits,
should serve as a preview to the main article. she takes a daring leap over a terrain fea-
ture known as "the camel's back" and
crashes. She hides her accident and the ex-
prompt The prompt to imagine
/imagine
prompt
Read the following story and identify 4 key moments Illusration 1: This is a cartoon-style scene
Image-Priming in the story. I want to generate 4 images based on the
key moments. Describe each key moment in adjec-
that depicts our protagonist, Yui Aragaki,
a character inspired by the famous Japa-
Generation tives and verbs so that I can describe it to an illustra-
tor. All the pictures should be described in a manner
nese actor. Yui is portrayed in full motor-
cycle gear, including a helmet and gog-
that they are independent. Replace Chan with Yui gles, standing next to a cool, cartoonish
Aragaki, a famous Japanese actor. motorcycle in an expansive, undulating
field. Yui's expressive face is a mix of ex-
citement and guilt. A highlight of the
background is the dirt trail with two
Read the following passage and create a succinct
The Camel's Back
Mindmap-Priming mind map in Markdown format for XMind compatibil-
ity, suitable for mobile phone display with a tree table
Generation structure. Chan's Decisions
• Ignored parents' warning
▪ Chose to ride her motorcycle unsu-
pervised
• Decided to tackle "the camel's back"
▪ Managed to perform the stunt
• Took risk of riding back despite pain
Figure 2: A figure showing how text-priming, image-priming, and mindmap-priming cues were gener-
ated using Generative-AI tools.
feeding in the respective text passage and generating the output. The resulting generative primes
are scalable and can be customized to readers’ preferences. More research is needed on the
quality and comprehensiveness of the text summaries and visualizations, as well as their ability
to assist readers in maintaining focus, comprehension, and recall. Moving forward, experiments
are needed with different types of distractions and reading contexts to further explore the
benefits and limitations of generative primes. We will also investigate the customization options
for these primes, allowing readers to tailor the summaries and visualizations to their preferences.
Ultimately, we hope to contribute to the development of reading interfaces that effectively
support readers in distractive environments and pave the way for a more seamless and enjoyable
reading experience in the digital age.
4. Conclusion
Our work defines and highlights the potential of generative primes, which include text sum-
maries and visualizations, to mitigate the challenges of reading in distractive environments. By
providing readers with informative cues before and after distractions occur, these generative
primes have the ability to enhance comprehension, recall, and engagement. Further research
may focus on the customization options and evaluate the effectiveness of these primes in differ-
ent reading contexts. Ultimately, we aim to contribute to the development of reading interfaces
that empower readers to navigate distractions and seamlessly continue their reading tasks.
Acknowledgements
We thank the participants of our studies as well as the continuous support by Adobe Research
and the team at the Documents Intelligence Lab, foremost Rajiv Jain and Jennifer Healey.
References
[1] L. Leiva, M. Böhmer, S. Gehring, A. Krüger, Back to the app: The costs of mobile application
interruptions, in: Proceedings of the 14th International Conference on Human-Computer
Interaction with Mobile Devices and Services, MobileHCI ’12, Association for Computing
Machinery, New York, NY, USA, 2012, p. 291–294. URL: https://doi.org/10.1145/2371574.
2371617. doi:10.1145/2371574.2371617 .
[2] A. Oulasvirta, S. Tamminen, V. Roto, J. Kuorelahti, Interaction in 4-second bursts: the
fragmented nature of attentional resources in mobile hci, in: Proceedings of the SIGCHI
conference on Human factors in computing systems, 2005, pp. 919–928.
[3] C. K. Foroughi, N. E. Werner, D. Barragán, D. A. Boehm-Davis, Interruptions disrupt
reading comprehension., Journal of Experimental Psychology: General 144 (2015) 704.
[4] S. T. Iqbal, B. P. Bailey, Investigating the effectiveness of mental workload as a predictor of
opportune moments for interruption, in: CHI ’05 Extended Abstracts on Human Factors
in Computing Systems, CHI EA ’05, Association for Computing Machinery, New York,
NY, USA, 2005, p. 1489–1492. URL: https://doi.org/10.1145/1056808.1056948. doi:10.1145/
1056808.1056948 .
[5] World Economic Forum, The rise and rise of media on your mobile phone
- in one chart, Available online at: https://www.weforum.org/agenda/2021/02/
media-consumption-mobile-phone/, 2021. Accessed: 10.11.2023.
[6] D. P. Brumby, A. L. Cox, J. Back, S. J. Gould, Recovering from an interruption: Investi-
gating speed- accuracy trade-offs in task resumption behavior., Journal of Experimental
Psychology: Applied 19 (2013) 95.
[7] G. Mark, V. M. Gonzalez, J. Harris, No task left behind? examining the nature of fragmented
work, in: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems,
CHI ’05, Association for Computing Machinery, New York, NY, USA, 2005, p. 321–330.
URL: https://doi.org/10.1145/1054972.1055017. doi:10.1145/1054972.1055017 .
[8] C. Schneegass, F. Draxler, Designing task resumption cues for interruptions in mobile
learning scenarios, in: Technology-Augmented Perception and Cognition, Springer, 2021,
pp. 125–181.
[9] T. Dingler, D. Kern, K. Angerbauer, A. Schmidt, Text priming - effects of text visualiza-
tions on readers prior to reading, in: R. Bernhaupt, G. Dalvi, A. Joshi, D. K. Balkrishan,
J. O’Neill, M. Winckler (Eds.), Human-Computer Interaction – INTERACT 2017, Springer
International Publishing, Cham, 2017, pp. 345–365.
[10] N. Srivastava, R. Jain, J. Healey, Z. Bylinskii, T. Dingler, Mitigating the effects of reading
interruptions by providing reviews and previews, in: Extended Abstracts of the 2021
CHI Conference on Human Factors in Computing Systems, CHI EA ’21, Association for
Computing Machinery, New York, NY, USA, 2021. URL: https://doi.org/10.1145/3411763.
3451610. doi:10.1145/3411763.3451610 .
[11] OpenAI, Chatgpt: Optimizing language models for dialogue, 2020.
[12] OpenAI, Gpt-4 technical report, 2023. arXiv:2303.08774 .
[13] K. Angerbauer, T. Dingler, D. Kern, A. Schmidt, Utilizing the effects of priming to
facilitate text comprehension, in: Proceedings of the 33rd Annual ACM Conference
Extended Abstracts on Human Factors in Computing Systems, CHI EA ’15, Associa-
tion for Computing Machinery, New York, NY, USA, 2015, p. 1043–1048. URL: https:
//doi.org/10.1145/2702613.2732914. doi:10.1145/2702613.2732914 .