The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index; none of the 15 sources its claims cite is checked for support yet.
Towards computational autobiographical narratives through human digital memories
Open accessAbstract
Lifelogging is an emergent technology which offers the ability to capture an individual's life experiences through digital means. While emphasis has been placed on taming such voluminous multimodal collections, it additionally opens new opportunities for retelling and sharing our personal life experiences. We explore these opportunities within the domain of lifelogging and present the research questions, challenges and considerations to be addressed to achieve meaningful autobiographical digital narratives within such collections.
Overview
CoChat Summary
Written by AI from the paper’s full text.
TL;DR
This position paper argues that lifelogging can support computational autobiographical narratives by exploiting the rich content and context in human digital memories. It outlines research questions and challenges across structural, representational, and presentational components, while reporting only planned work rather than completed results.
Key findings
- The paper asserts that lifelogs contain enough content and context to enable semi-automatic narration of biographical events, but that achieving understanding of the story remains the major challenge.
- It identifies three components for computed narratives—structural, representational, and presentational—and argues that lifelog storytelling should likely be event-based, with automatic identification of causal chains of events.
- It reports that current lifelog retellings, such as rapid playback of SenseCam images or animated slideshows, are “only inherently meaningful to the owner” and find little resonance with others.
- It cites prior work including Harper et al.’s study with six participants on user-created digital narratives from SenseCam images, and notes that manual composition is questionable given the volume of lifelog collections.
Methods
- Conceptual/position paper: reviews the MEMEX vision, current lifelogging tools, and prior storytelling/lifelog studies, then outlines research questions and considerations for computational autobiographical narratives.
- Planned data collection: large-scale realistic lifelog collections from four participants over a one-year period, capturing desktop activity/content, mobile activity/content, personal context via Bluetooth/GPS/wireless/GSM, SenseCam images, and biometric readings.
- Planned analysis: user studies to investigate life-story practices, followed by implementation of a semi-automatic narrative system to construct life stories from causally related events and evaluate reflection and sharing.
Limitations
- The paper states that current retelling techniques are ineffective for communicating life stories to others and that manual composition of narratives is questionable given collection volume.
- It states that prior work such as Harper et al. offers insight into perception of narratives rather than their composition, and that low-sample capture cannot provide the richness needed for reliable semantic knowledge.
- Evident from the text: no empirical results are reported; the lifelog collection, user studies, and semi-automatic narrative system are described as current or planned work, not completed evaluations.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
20 Own interpretation · 14 Sources not found · 1 Own result
In the paper
“Previous research in this domain, such as that of Doherty and Smeaton [7] that segments the artifacts of a lifelog into higherlevel discrete units or 'events', has focused on the management of such rich and voluminous collections.”
§ Towards Computational Autobiographical Narratives through Human Digital Memories > 3. CURRENT STATE OF THE ART
What the sources say
- Not matchedcites [7]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“However, it is unlikely that the commonly used structures in computational narratives, such as those used by Brooks [3] will be directly applicable in this domain.”
§ Towards Computational Autobiographical Narratives through Human Digital Memories > 5.2 Structural Considerations
What the sources say
- Not matchedcites [3]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“This will require extension of the work of [7], which has solely focused on SenseCam images and not the full range of content within a lifelog.”
§ Towards Computational Autobiographical Narratives through Human Digital Memories > 5.2 Structural Considerations
What the sources say
- Not matchedcites [7]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“With a series of related events contained within the one story, consequently the causality of these events becomes extremely important to the structure of that narrative.”
§ Towards Computational Autobiographical Narratives through Human Digital Memories > 5.2 Structural Considerations
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The retelling becoming a passive experience for them.”
§ Towards Computational Autobiographical Narratives through Human Digital Memories > 5.3 Representational Considerations
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Probably not a substantial claim. 25
- It may state two separate claims as one. 9
Create a free account to see these claims.
Create a free account to see these assumptions.
3 more claims
Create a free account to see all 35 claims and every source verdict.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Towards Computational Autobiographical Narratives through Human Digital Memories > 4. STORY TELLING AND LIFELOGS
“Harper et al. [10] conducted a study with six participants into user-created digital narratives composed from SenseCam captured images.”
§ Towards Computational Autobiographical Narratives through Human Digital Memories > References
“9. Harper R., Randall, D., Smyth N., Evans, C., Heledd, L. and Moore, R. Thanks for the Memory, In Proc. BCS HCI 2007. 10. Hodges, S., et al. SenseCam: a Retrospective Memory Aid, In Proc. Ubicomp 2006, pp. 177-193.”
Citations
Cites
(1983) · Medical Entomology and Zoology · Cited by 6,051
SenseCam: A Retrospective Memory Aid
Hodges, S. E., Williams, L., Berry, E., Izadi, S., Srinivasan, J., Butler, A., Smyth, G., Kapur, N., & Wood, K. R. (2006) · Lecture notes in computer science · doi:10.1007/11853565_11 · Cited by 767
The challenge problem for automated detection of 101 semantic concepts in multimedia
Snoek, C. G. M., Worring, M., van Gemert, J. C., Geusebroek, J., & Smeulders, A. W. M. (2006) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/1180639.1180727 · Cited by 621
(1997) · Choice Reviews Online · doi:10.5860/choice.34-3707 · Cited by 308
Kearney, R. (2002) · Routledge eBooks · doi:10.4324/9780203453483 · Cited by 292
Automatically Segmenting LifeLog Data into Events
Doherty, A., & Smeaton, A. F. (2008) · International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) · doi:10.1109/wiamis.2008.32 · Cited by 149
Bell, G., & Gemmell, J. (2007) · Scientific American · doi:10.1038/scientificamerican0307-58 · Cited by 130
Brooks, K. M. (1996) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/244130.244233 · Cited by 73
Telling Stories with Mylifebits
Gemmell, J., Aris, A., & Lueder, R. (2005) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2005.1521726 · Cited by 68
Harper, R. H. R., Randall, D. W., Smythe, N., Evans, C., Heledd, L., & Moore, R. (2007) · Electronic workshops in computing · doi:10.14236/ewic/hci2007.56 · Cited by 59
Communicating everyday experiences
Appan, P., Sundaram, H., & Birchfield, D. A. (2004) · doi:10.1145/1026633.1026638 · Cited by 37
The Context Quintet: Narrative Elements Applied to Context Awareness 1
Brooks, K. (2003) · Cited by 36
Venturing into the Labyrinth: the Information Retrieval Challenge of Human Digital Memories
Kelly, L., & Jones, G. J. F. (2007) · Arrow@dit (Dublin Institute of Technology) · Cited by 12
Self-citationThe Information Retrieval Challenge of Human Digital Memories
Kelly, L. (2007) · Electronic Workshops in Computing · doi:10.14236/ewic/fdia2007.17
Research works printed but not linked: 4
- Brooks K., 2003, Proc. Human Computer Interactions International '03
- 10.5555/1531407.1531418 · DOI
- Kelly L., 2007, Proc. MEMOS Workshop, BCS HCI
- Tulving E., 1984, Oxford Clarendon Press
Cited by
LifeLogging: Personal Big Data
Gurrin, C. G., Smeaton, A. F., & Doherty, A. (2014) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000033 · Cited by 459
Building digital life stories for memory support
Kikhia, B., Hallberg, J., Bengtsson, J. E., Sävenstedt, S., & Synnes, K. (2010) · International Journal of Computers in Healthcare · doi:10.1504/ijcih.2010.037460 · Cited by 41
Creating human digital memories with the aid of pervasive mobile devices
Dobbins, C., Merabti, M., Fergus, P., & Llewellyn-Jones, D. (2013) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2013.10.009 · Cited by 34
Byrne, D., Kelliher, A., & Jones, G. J. F. (2011) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/1978942.1979162 · Cited by 26
Self-citationInformation access tasks and evaluation for personal lifelogs
Jones, G. J. F., Gurrin, C. G., Kelly, L., Byrne, D., & Chen, Y. (2008) · Arrow@dit (Dublin Institute of Technology) · Cited by 11
Self-citation
Metadata
- Authors
- Byrne, D., & Jones, G. J. F.
- Affiliations
- Dublin City University (IE)
- Venue
- Proceedings of the 2nd ACM international workshop on Story representation, mechanism and context
- Publisher
- ACM
- Published
- 2008-10-31
- Pages
- 9-12
- OpenAlex
- W2158303744
- Cited by
- 24
- References
- 13
- Citations by year
- 2018: 1 · 2016: 1 · 2015: 1 · 2014: 2 · 2013: 5 · 2012: 4
- FWCI
- 2.53
- Type
- conference paper
- Language
- en
- Open access
- green
- orcid.org
- Locations
- Dublin City University Open Access Institutional Repository (Dublin City University) (submittedVersion)
- Arrow@dit (Dublin Institute of Technology) (submittedVersion, cc-by-nc-sa)
- Funders
- Irish Research Council for Science, Engineering and Technology
- Irish Research Council
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Social Sciences › Education › Digital Storytelling and Education
- Social Sciences › Psychology › Developmental and Educational Psychology › Identity, Memory, and Therapy
- Keywords
- lifelogging, autobiographical narrative, digital memory, personal experience, multimodal data, narrative retelling, computational narrative
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
