diff --git a/brainsteam/content/annotations/2022/11/27/1669554883.md b/brainsteam/content/annotations/2022/11/27/1669554883.md
new file mode 100644
index 0000000..3425f4d
--- /dev/null
+++ b/brainsteam/content/annotations/2022/11/27/1669554883.md
@@ -0,0 +1,59 @@
+---
+date: '2022-11-27T13:14:43'
+hypothesis-meta:
+  created: '2022-11-27T13:14:43.604240+00:00'
+  document:
+    title:
+    - Analysis_of_REF_impact.pdf
+  flagged: false
+  group: __world__
+  hidden: false
+  id: dTjBdG5VEe2sq0cgSuwbjw
+  links:
+    html: https://hypothes.is/a/dTjBdG5VEe2sq0cgSuwbjw
+    incontext: https://hyp.is/dTjBdG5VEe2sq0cgSuwbjw/webarchive.nationalarchives.gov.uk/ukgwa/20170712131025mp_/http://www.hefce.ac.uk/media/HEFCE,2014/Content/Pubs/Independentresearch/2015/Analysis,of,REF,impact/Analysis_of_REF_impact.pdf
+    json: https://hypothes.is/api/annotations/dTjBdG5VEe2sq0cgSuwbjw
+  permissions:
+    admin:
+    - acct:ravenscroftj@hypothes.is
+    delete:
+    - acct:ravenscroftj@hypothes.is
+    read:
+    - group:__world__
+    update:
+    - acct:ravenscroftj@hypothes.is
+  tags:
+  - lda
+  - comprehensive impact
+  target:
+  - selector:
+    - end: 39662
+      start: 39458
+      type: TextPositionSelector
+    - exact: Topic modelling was used to determine common topics across the wholecorpus.
+        Sixty-five topics were found (of which 60 were used) using theApache Mallet
+        Toolkit Latent Dirichlet Allocation (LDA) algorithm.
+      prefix: s to answer specific challenges.
+      suffix: 12Topics are based on the freque
+      type: TextQuoteSelector
+    source: https://webarchive.nationalarchives.gov.uk/ukgwa/20170712131025mp_/http://www.hefce.ac.uk/media/HEFCE,2014/Content/Pubs/Independentresearch/2015/Analysis,of,REF,impact/Analysis_of_REF_impact.pdf
+  text: The authors used LDA with k=60 across full text case studies. The Apache Mallet
+    implementation was used.
+  updated: '2022-11-27T13:14:43.604240+00:00'
+  uri: https://webarchive.nationalarchives.gov.uk/ukgwa/20170712131025mp_/http://www.hefce.ac.uk/media/HEFCE,2014/Content/Pubs/Independentresearch/2015/Analysis,of,REF,impact/Analysis_of_REF_impact.pdf
+  user: acct:ravenscroftj@hypothes.is
+  user_info:
+    display_name: James Ravenscroft
+in-reply-to: https://webarchive.nationalarchives.gov.uk/ukgwa/20170712131025mp_/http://www.hefce.ac.uk/media/HEFCE,2014/Content/Pubs/Independentresearch/2015/Analysis,of,REF,impact/Analysis_of_REF_impact.pdf
+tags:
+- lda
+- comprehensive impact
+- hypothesis
+type: annotation
+url: /annotations/2022/11/27/1669554883
+
+---
+
+
+
+ <blockquote>Topic modelling was used to determine common topics across the wholecorpus. Sixty-five topics were found (of which 60 were used) using theApache Mallet Toolkit Latent Dirichlet Allocation (LDA) algorithm.</blockquote>The authors used LDA with k=60 across full text case studies. The Apache Mallet implementation was used.
\ No newline at end of file