Update README.md

README.md

@@ -10,37 +10,59 @@ tags:
 
 # dwulff/mpnet-personality
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+This is a [sentence-transformers](https://www.SBERT.net) model that maps personality-related items or texts into a 768-dimensional dense vector space and can be used for many tasks in personality psychology.
 
-<!--- Describe your model here -->
+The model has been generated by fine-tuning [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) using unsigned empirical correlations of 200k pairs of personality items. As a result, the model encodes the content of personality-related texts independent of the direction (e.g., negation).  
 
-## Usage (Sentence-Transformers)
+See [Wulff & Mata (2024)](https://osf.io/preprints/psyarxiv/9h7aw) (see [Supplement](https://osf.io/z47qs/)) for details. For a similar approach, see [Hommel & Arslan (2024)](https://osf.io/preprints/psyarxiv/kjuce).
 
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+## Usage
+
+Make sure [sentence-transformers](https://www.SBERT.net) is installed:
 
 ```
+# latest version
 pip install -U sentence-transformers
+
+# latest dev version
+pip install git+https://github.com/UKPLab/sentence-transformers.git
 ```
 
-Then you can use the model like this:
+You can extract embeddings in the following way:
 
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('dwulff/mpnet-personality')
+# personality sentences
+sentences = ["Rarely think about how I feel.", "Make decisions quickly."]
+
+# load model
+model = SentenceTransformer('Fissionships/mpnet-personality')
+
+# extract embeddings
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
 
+## Evaluation Results
 
+The model has been evaluated on public personality data. For standard personality inventories, such as the BIG5 or HEXACO inventories, the model predicts the empirical correlations between personality items at Pearson r ~ .6 and empirical correlations between scales at Pearson r ~ .8. 
 
-## Evaluation Results
+Performance can be higher on the many common personality items it has been trained on due to memorization. Performance will be worse for more specialized personality assessments and texts beyond personality items.
 
-<!--- Describe how your model was evaluated -->
+See [Wulff & Mata (2024)](https://osf.io/preprints/psyarxiv/9h7aw) (see [Supplement](https://osf.io/z47qs/)) for details. 
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=dwulff/mpnet-personality)
+## Citing
 
+```
+@article{wulff2024jinglejangle,
+  author       = {Wulff, Dirk U. and Mata, Rui},
+  title        = {Automated jingle–jangle detection: Using embeddings to tackle taxonomic incommensurability},
+  journal      = {PsyArViv},
+  doi          = {https://doi.org/10.31234/osf.io/9h7aw}
+}
+
+```
 
 ## Training
 The model was trained with the parameters:
@@ -84,6 +106,3 @@ SentenceTransformer(
 )
 ```
 
-## Citing & Authors
-
-<!--- Describe where people can find more information -->