ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives
Open accessThe DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index; none of the 5 sources its claims cite is checked for support yet.
Overview
CoChat Summary
TL;DR
ATEM is a framework for detecting emerging interdisciplinary topics in scientific archives by combining dynamic topic modeling with dynamic graph embedding over topic-citation graphs. Experiments on DBLP (over five million computer science articles, 2000–2020) show that citation-context embedding neighbors yield higher emergence predictability than co-citation-linked topic pairs.
Key findings
- ATEM can efficiently detect emerging cross-disciplinary topics within the DBLP archive of over five million computer science articles.
- In a proof-of-concept sample of 200 evolving topics with n=10 topics per period, NeighborTopics (new embedding nearest neighbors, max distance 0.2, min embedding norm 0.22) had higher predictability than LinkedTopics (citation-path-connected pairs). On average, 75% of emerging topics have 1.25/0.75 = 1.66 times more publications after emergence than before; 50% of NeighborTopics have 2.6/0.4 = 6.2 more publications after emergence than before, whereas the ratio is 1 for LinkedTopics.
- The average number of NeighborTopics decreases over time and average embedding distance increases; predictability decreases with increasing distance and strongly decreases in time; average emergence is positive before 2016 and becomes negative afterward.
- Example: topics T680C6 and T661C6 emerge in 2013 as near embedding neighbors with a maximal distance of 0.2, and most common documents for the pair were published after 2013.
Methods
- ATEM extracts evolving topics by combining content-based document clustering (Doc2Vec embeddings, UMAP, HDBSCAN) and citation-based clustering (Leiden community detection), intersecting the two cluster types, splitting clusters into time periods, and representing topics via nearest words and class-based TF-IDF.
- It builds a dynamic topic-citation graph by projecting document citation links into topic space, then applies OnlineNode2Vec dynamic node embeddings and cosine similarity to define emerging topics as topic pairs whose context distance crosses a threshold at a given period.
- The implementation is applied to DBLP with 5M scientific articles published between 2000 and 2020; the proof of concept randomly samples 200 evolving topics, generates NeighborTopics and LinkedTopics sets of n=10 per period, and compares their predictability based on document distribution before and after emergence.
Limitations
- Stated: the conclusion that analyzed topics get more diverse over time must be confirmed by deeper analysis of bias introduced by the dynamic computation algorithm; emergence values are influenced by the relative length of past and future covered by the archive, with average emergence positive before 2016 and negative afterward; future work is needed on other datasets and domains.
- Evident: the evaluation is a proof of concept on one dataset with one main comparison baseline (co-citation/LinkedTopics), and no ground-truth emerging topics or precision/recall metrics are reported; the predictability metric may be affected by archive time coverage and embedding thresholds.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures















Verification
Claims the paper makes
0 Valid · 0 Not valid · 3 Not checked · 36 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our experiments show that ATEM can efficiently detect emerging crossdisciplinary topics within the DBLP archive of over five million computer science articles.”
§ ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives * > Abstract
plainstates a cause- 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.
- Rests on 4 assumptions not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We can see, for example, topic T661C6 appears in 2013 as a near embedding neighbor of evolving topic T680C6 (with a maximal distance of 0.2).”
§ ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives * > 5 EMERGING TOPIC DETECTION
hedgedstates an associationSingle case- 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.
- Rests on an assumption not shown here.
A result the paper reports from its own data — 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 result shows that most of the top relevant documents for emerging topic (T680C6, T661C6) have been published after its emergence period 2013.”
§ ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives * > 5 EMERGING TOPIC DETECTION
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While the number of 𝐿𝑖𝑛𝑘𝑒𝑑𝑇𝑜𝑝𝑖𝑐𝑠 increases with time, we observed that the average number of 𝑁 𝑒𝑖𝑔ℎ𝑏𝑜𝑟𝑇𝑜𝑝𝑖𝑐𝑠 decreases and the average embedding distance increases.”
§ ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives * > 7 PROOF OF CONCEPT
plainstates a cause- 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.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, as we show in our experiments, we can define functions to estimate the past and future documents using the topic model or a search engine like Google Scholar.”
§ ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives * > 5 EMERGING TOPIC DETECTION
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.
20 more claims
Create a free account to see all 39 claims and to verify the 5 references still open.
- The quote only partly states this claim. 1
- It may state two separate claims as one. 4
- Probably not a substantial claim. 10
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 major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives * > 8 CONCLUSION
“if the context distance 𝑑𝑖𝑠𝑡 (𝑡 𝑘 𝑖 , 𝑡 𝑘 𝑗 ) at period 𝑝 𝑘 is above a given threshold 𝜙 and below this threshold before 𝑝 𝑘 .”
§ ATEM: A Topic Evolution Model for the Detection of Emerging Topics in Scientific Archives * > 6.3 Extracting Emerging Topics
“it allows us to identify evolving topics (𝑡 𝑥 , 𝑡 𝑦 ) when the distance between two evolving topics 𝑡 𝑥 and 𝑡 𝑦 is less than a given threshold.”
Citations
Cites
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
The Structure of Scientific Revolutions: 50th Anniversary Edition
Kuhn, T. S., & Hacking, I. (2012) · doi:10.7208/chicago/9780226458144.001.0001 · Cited by 21,170
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · Advances in Neural Information Processing Systems 14 · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,223
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
McInnes, L., Healy, J., & Melville, J. (2018) · arXiv · doi:10.48550/arxiv.1802.03426 · Cited by 7,101
Chen, C. (2006) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.20317 · Cited by 6,433
From Louvain to Leiden: guaranteeing well-connected communities
Traag, V. A., Waltman, L., & van Eck, N. J. (2019) · Scientific Reports · doi:10.1038/s41598-019-41695-z · Cited by 5,635
Blei, D. M., & Lafferty, J. D. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143859 · Cited by 3,173
Density-Based Clustering Based on Hierarchical Density Estimates
Campello, R. J. G. B., Moulavi, D., & Sander, J. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-37456-2_14 · Cited by 2,680
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications
Cai, H., Zheng, V. W., & Chang, K. C.-C. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2807452 · Cited by 2,034
Graph embedding techniques, applications, and performance: A survey
Goyal, P., & Ferrara, E. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.03.022 · Cited by 1,801
BERTopic: Neural topic modeling with a class-based TF-IDF procedure
Grootendorst, M. (2022) · arXiv · doi:10.48550/arxiv.2203.05794 · Cited by 1,423
Top2Vec: Distributed Representations of TopicsPreprint
Angelov, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.09470 · Cited by 944
The DBLP Computer Science Bibliography: Evolution, Research Issues, Perspectives
Ley, M. (2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-45735-6_1 · Cited by 436
Identifying emerging topics in science and technology
Small, H., Boyack, K. W., & Klavans, R. (2014) · Research Policy · doi:10.1016/j.respol.2014.02.005 · Cited by 378
Hou, J., Yang, X., & Chen, C. (2018) · Scientometrics · doi:10.1007/s11192-018-2695-9 · Cited by 368
Continuous Time Dynamic Topic Models
Wang, C., Blei, D. M., & Heckerman, D. E. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.3298 · Cited by 311
Topic modeling algorithms and applications: A survey
Abdelrazek, A., Eid, Y., Gawish, E., Medhat, W., & Hassan, A. (2023) · Information Systems · doi:10.1016/j.is.2022.102131 · Cited by 304
Rossetto, D. E., Bernardes, R. C., Borini, F. M., & Gattaz, C. C. (2018) · Scientometrics · doi:10.1007/s11192-018-2709-7 · Cited by 214
Phylomemetic Patterns in Science Evolution—The Rise and Fall of Scientific Fields
Chavalarias, D., & Cointet, J. (2013) · PLoS ONE · doi:10.1371/journal.pone.0054847 · Cited by 183
Detecting topic evolution in scientific literature: how can citations help?
He, Q., Chen, B., Pei, J., Qiu, B., Mitra, P., & Giles, L. (2009) · Proceedings of the 18th ACM conference on Information and knowledge management · doi:10.1145/1645953.1646076 · Cited by 170
The Dynamic Embedded Topic ModelPreprint
Dieng, A. B., Ruiz, F. J. R., & Blei, D. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.05545 · Cited by 168
dynnode2vec: Scalable Dynamic Network Embedding
Mahdavi, S., Khoshraftar, S., & An, A. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8621910 · Cited by 154
Trend analysis and change point techniques: a survey
Sharma, S., Swayne, D., & Obimbo, C. (2016) · Energy Ecology and Environment · doi:10.1007/s40974-016-0011-1 · Cited by 136
Tracking dynamics of topic trends using a finite mixture model
Morinaga, S., & Yamanishi, K. (2004) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1014052.1016919 · Cited by 124
Breitzman, A., & Thomas, P. (2015) · Research Policy · doi:10.1016/j.respol.2014.06.006 · Cited by 92
Topic evolution and social interactions
Zhou, D. X., Ji, X., Hongyuan Zha, B., & Giles, C. L. (2006) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/1183614.1183653 · Cited by 87
The web of topics: discovering the topology of topic evolution in a corpus
Jo, Y., Hopcroft, J. E., & Lagoze, C. (2011) · International World Wide Web Conference (WWW) · doi:10.1145/1963405.1963444 · Cited by 84
Soriano, A. S., Álvarez, C. L., & Valdés, R. M. T. (2018) · Scientometrics · doi:10.1007/s11192-018-2651-8 · Cited by 65
Tracking the dynamics of co-word networks for emerging topic identification
Huang, L., Chen, X., Ni, X., Liu, J., Cao, X., & Wang, C. (2021) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2021.120944 · Cited by 64
AUGUR: Forecasting the Emergence of New Research Topics
Salatino, A. A., Osborne, F., & Motta, E. (2018) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/3197026.3197052 · Cited by 59
Mapping the technology evolution path: a novel model for dynamic topic detection and tracking
Liu, H., Chen, Z., Tang, J., Zhou, Y. J., & Liu, S. (2020) · Scientometrics · doi:10.1007/s11192-020-03700-5 · Cited by 58
Node embeddings in dynamic graphs
Béres, F., Kelen, D. M., Pálovics, R., & Benczúr, A. A. (2019) · Applied Network Science · doi:10.1007/s41109-019-0169-5 · Cited by 53
INNOVATION IN REGULATORY SCIENCE: EVOLUTION OF A NEW SCIENTIFIC DISCIPLINE
Moghissi, A. A., Straja, S. R., Love, B. R., Bride, D. K., & Stough, R. R. (2014) · Technology & Innovation · doi:10.3727/194982414x14096821477027 · Cited by 42
Finding topic trends in digital libraries
Bolelli, L., Ertekin, Ş., Zhou, D. X., & Giles, C. L. (2009) · ACM/IEEE Joint Conference on Digital Libraries · doi:10.1145/1555400.1555411 · Cited by 40
Hotness prediction of scientific topics based on a bibliographic knowledge graph
Huo, C., Ma, S., & Liu, X. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.102980 · Cited by 37
Evolving Networks and Social Network Analysis Methods and Techniques
Cordeiro, M., Sarmento, R. P., Brazdil, P., & Gama, J. (2018) · Social Media and Journalism - Trends, Connections, Implications · doi:10.5772/intechopen.79041 · Cited by 32
How are topics born? Understanding the research dynamics preceding the emergence of new areas
Salatino, A. A., Osborne, F., & Motta, E. (2017) · PeerJ Computer Science · doi:10.7717/peerj-cs.119 · Cited by 31
Zhang, C., & Guan, J. (2017) · Scientometrics · doi:10.1007/s11192-017-2503-y · Cited by 28
Leap2Trend: A Temporal Word Embedding Approach for Instant Detection of Emerging Scientific Trends
Dridi, A., Gaber, M. M., Azad, R. M. A., & Bhogal, J. (2019) · IEEE Access · doi:10.1109/access.2019.2957440 · Cited by 28
Discovering topic structures of a temporally evolving document corpus
Beykikhoshk, A., Arandjelović, O., Phung, D., & Venkatesh, S. (2018) · Knowledge and Information Systems · doi:10.1007/s10115-017-1095-4 · Cited by 24
Andrei, V., & Arandjelović, O. (2016) · EURASIP Journal on Bioinformatics and Systems Biology · doi:10.1186/s13637-016-0050-0 · Cited by 21
Luhmann, N. (2017) · Epistemology & Philosophy of Science · doi:10.5840/eps201752240 · Cited by 20
dynnode2vec: Scalable Dynamic Network EmbeddingPreprint
Mahdavi, S., Khoshraftar, S., & An, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.02356 · Cited by 20
Generating process of emerging topics in the life sciences
Ohniwa, R. L., & Hibino, A. (2019) · Scientometrics · doi:10.1007/s11192-019-03248-z · Cited by 19
ANTM: Aligned Neural Topic Models for Exploring Evolving Topics
Rahimi, H., Naacke, H., Constantin, C., & Amann, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-662-69603-3_3 · Cited by 19
Self-citationModeling discrete dynamic topics
Bahrainian, S. A., Mele, I., & Crestani, F. (2017) · ACM Symposium on Applied Computing · doi:10.1145/3019612.3019673 · Cited by 18
Balili, C., Lee, U., Segev, A., Kim, J., & Ko, M. (2020) · IEEE Access · doi:10.1109/access.2020.3000948 · Cited by 18
Identifying dynamic knowledge flow patterns of business method patents with a hidden Markov model
An, Y., Han, M., & Park, Y. (2017) · Scientometrics · doi:10.1007/s11192-017-2514-8 · Cited by 15
ANTM: An Aligned Neural Topic Model for Exploring Evolving TopicsPreprint
Rahimi, H., Naacke, H., Constantin, C., & Amann, B. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.01501 · Cited by 14
Self-citationAn Analytic Graph Data Model and Query Language for Exploring the Evolution of Science
Li, K., Naacke, H., & Amann, B. (2021) · Big Data Research · doi:10.1016/j.bdr.2021.100247 · Cited by 10
Self-citationJung, S., & Segev, A. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110020 · Cited by 7
DAC: Descendant-aware clustering algorithm for network-based topic emergence prediction
Jung, S., & Segev, A. (2022) · Journal of Informetrics · doi:10.1016/j.joi.2022.101320 · Cited by 6
(1962)
How are topics born? Understanding the research dynamics preceding the emergence of new areas
Salatino, A. A., Osborne, F., & Motta, E. (2016) · doi:10.7287/peerj.preprints.2306v1
Dac: Descendant-Aware Clustering Algorithm for Network-Based Topic Emergence Prediction
Jung, S., & Segev, A. (2022) · doi:10.2139/ssrn.4043730
Research works printed but not linked: 2
- K. R. Popper et al., Objective Knowledge: An Evolutionary Approach, vol. 49. Claren- don press Oxford, 1979.
- M. Grootendorst, "Bertopic: Neural topic modeling with a class-based tf-idf procedure, " arXiv preprint arXiv:2203.05794, 2022. · arXiv
Cited by
ANTM: Aligned Neural Topic Models for Exploring Evolving Topics
Rahimi, H., Naacke, H., Constantin, C., & Amann, B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-662-69603-3_3 · Cited by 19
Self-citationEvaluation of unsupervised static topic models’ emergence detection ability
Li, X., Esposito, C. D., Groth, P., Sitruk, J., Szatmari, B., & Wijnberg, N. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2875 · Cited by 9
Efficient topic modeling for large-scale community question and answer websites
Prabha, S., & Sardana, N. (2024) · International Journal of Systems Assurance Engineering and Management · doi:10.1007/s13198-024-02641-z
Arabic Topic Detection: A Comprehensive Review of Recent Advances
Dawood, N. S., & Mahmood, S. A. (2025) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.3424
Tracking Academic Topic Evolution From the Perspective of Author Interest Shifts
Jiang, W., Zhang, Y. X., Wang, M., Mo, H., Hussain, O. K., Dong, D., & Zhang, W. (2025) · IEEE International Conference on e-Business Engineering (ICEBE) · doi:10.1109/icebe68123.2025.00015
Metadata
- Authors
- Rahimi, H., Naacke, H., Constantin, C., & Amann, B.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Corresponding author
- Rahimi, Hamed
- Venue
- Studies in Computational Intelligence
- Publisher
- Springer Nature Switzerland
- Published
- 2024
- Volume
- 1143
- Pages
- 332-343
- ISSN
- 1860-949X (ISSN-L)
- 1860-9503
- OpenAlex
- W4391973680
- Cited by
- 9
- References
- 51
- Citations by year
- 2026: 3 · 2025: 3 · 2024: 3
- FWCI
- 0.78
- Type
- conference paper
- Language
- en
- Open access
- green
- inria.hal.science
- Licence
- cc-by
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Studies in computational intelligence (publishedVersion)
- HAL (submittedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Social Sciences › Library and Information Sciences › scientometrics and bibliometrics research
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Keywords
- topic evolution, emerging research areas, dynamic topic modeling, dynamic graph embedding, citation context, citation dynamics, DBLP, computer science literature, scientific archives
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 2026-11-18, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-18 (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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.