=========
SocialVec
=========
.. image:: https://img.shields.io/pypi/v/socialvec.svg
:target: https://pypi.python.org/pypi/socialvec
The **SocialVec** package provides pre-trained embeddings for approximately 200,000 popular Twitter accounts. **SocialVec** is a framework for learning social entity embeddings, derived from a large-scale Twitter dataset encompassing 1.3 million users and the accounts they follow.
* Free software: MIT license
What are SocialVec Embeddings?
==============================
**SocialVec embeddings** are low-dimensional vector representations of popular Twitter accounts. These embeddings are trained on co-occurrence patterns observed in the Twitter social network. Accounts frequently co-followed by users are considered socially related, making these embeddings similar to word embeddings where words in similar contexts have similar vector representations.
Package Features
================
This package includes the following features:
- **Access to pre-trained SocialVec embeddings:**
- Pre-trained embeddings for approximately 200,000 popular Twitter accounts.
- Embeddings are 100-dimensional, trained using the Skip-gram model with negative sampling (SGNS).
- **Entity similarity computation:**
- Calculate cosine similarity between SocialVec embeddings to assess social similarity between entities.
- Enables tasks like:
- Identifying similar entities (e.g., universities similar to UC Berkeley).
- Recommending Twitter accounts based on existing followings.
- Assessing the political leaning of news sources.
- **Entity analogy exploration:**
- Experiment with relational arithmetic on SocialVec embeddings to explore entity analogies, similar to word analogies.
Potential Applications
======================
The **SocialVec** package can be used for a wide range of tasks, including:
- **Recommendation systems:** Recommending Twitter accounts or other content based on user social affinity captured by the embeddings.
- **Social analysis:** Investigating social trends and relationships between entities on Twitter.
- **Bias detection:** Identifying potential biases in social media content or user behavior based on social context.
- **Inferring personal traits:** Predicting user characteristics like age, gender, or political leaning based on their social connections on Twitter.
Examples
========
Here are some practical examples of what you can do with **SocialVec**:
- **Finding similar entities:** Retrieve universities similar to UC Berkeley based on the cosine similarity of their SocialVec embeddings.
- **Recommending Twitter accounts:** Suggest accounts similar to those followed by a specific user, leveraging social context captured in the embeddings.
- **Assessing political leaning:** Determine the political bias of news sources by comparing their similarity to embeddings of politically polarized accounts (e.g., accounts of prominent politicians).
- **Exploring entity analogies:** Complete analogies like *"X-Factor : Simon Cowell :: The Voice : ?"* using vector arithmetic on SocialVec embeddings.
Advantages of SocialVec
=======================
- **Captures social world knowledge:** Unlike embeddings derived from factual knowledge bases like Wikipedia or Wikidata, SocialVec embeddings reflect relationships between entities based on social media interactions.
- **Wider coverage:** SocialVec represents a broader range of entities, as many Twitter accounts do not have corresponding Wikipedia pages.
Notes
=====
This README covers the pre-trained embeddings provided by the package. Specific implementation details and additional functionality will be defined as part of the package's development.
Credits
=======
This package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.
.. _Cookiecutter: https://github.com/audreyr/cookiecutter
.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage
History
-------
0.1.0 (2022-09-29)
------------------
* First release on PyPI.
0.1.1 (2022-09-29)
------------------
* Include config.yaml in the distribution.
0.1.2 (2022-10-02)
------------------
* Rearrange config.yaml
* Support multiple versions of the SocialVec model
* Fix bug when searching for similarity using username
0.1.3 (2022-10-14)
------------------
* Initial version of SocialVecClassifier
0.1.4 (2022-11-08)
------------------
* Updates to SocialVecClassifier
0.1.5 (2023-11-07)
------------------
* Update a dedicated model for the SocialVecClassifier (2020c)
0.1.6 (2023-11-09)
------------------
* Modify requirements to support more up-to-date python versions
0.1.7 (2024-10-22)
------------------
* Add the option to load the model to RAM in case there is no write permission to the package folder (which
0.1.7.1 (2024-10-22)
--------------------
* Add pypi documentation
Raw data
{
"_id": null,
"home_page": "https://github.com/nirlotan/socialvec",
"name": "socialvec",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "socialvec",
"author": "Nir Lotan",
"author_email": "nir.lotan@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/94/fa/9ae5c92a3d0d616ee5e1f723621e53c7ee4649d2e79ad977a92e1ad415c8/socialvec-0.1.7.1.tar.gz",
"platform": null,
"description": "=========\r\nSocialVec\r\n=========\r\n\r\n.. image:: https://img.shields.io/pypi/v/socialvec.svg\r\n :target: https://pypi.python.org/pypi/socialvec\r\n\r\nThe **SocialVec** package provides pre-trained embeddings for approximately 200,000 popular Twitter accounts. **SocialVec** is a framework for learning social entity embeddings, derived from a large-scale Twitter dataset encompassing 1.3 million users and the accounts they follow.\r\n\r\n* Free software: MIT license\r\n\r\nWhat are SocialVec Embeddings?\r\n==============================\r\n\r\n**SocialVec embeddings** are low-dimensional vector representations of popular Twitter accounts. These embeddings are trained on co-occurrence patterns observed in the Twitter social network. Accounts frequently co-followed by users are considered socially related, making these embeddings similar to word embeddings where words in similar contexts have similar vector representations.\r\n\r\nPackage Features\r\n================\r\n\r\nThis package includes the following features:\r\n\r\n- **Access to pre-trained SocialVec embeddings:**\r\n\r\n - Pre-trained embeddings for approximately 200,000 popular Twitter accounts.\r\n - Embeddings are 100-dimensional, trained using the Skip-gram model with negative sampling (SGNS).\r\n\r\n- **Entity similarity computation:**\r\n\r\n - Calculate cosine similarity between SocialVec embeddings to assess social similarity between entities.\r\n - Enables tasks like:\r\n\r\n - Identifying similar entities (e.g., universities similar to UC Berkeley).\r\n - Recommending Twitter accounts based on existing followings.\r\n - Assessing the political leaning of news sources.\r\n\r\n- **Entity analogy exploration:**\r\n\r\n - Experiment with relational arithmetic on SocialVec embeddings to explore entity analogies, similar to word analogies.\r\n\r\nPotential Applications\r\n======================\r\n\r\nThe **SocialVec** package can be used for a wide range of tasks, including:\r\n\r\n- **Recommendation systems:** Recommending Twitter accounts or other content based on user social affinity captured by the embeddings.\r\n- **Social analysis:** Investigating social trends and relationships between entities on Twitter.\r\n- **Bias detection:** Identifying potential biases in social media content or user behavior based on social context.\r\n- **Inferring personal traits:** Predicting user characteristics like age, gender, or political leaning based on their social connections on Twitter.\r\n\r\nExamples\r\n========\r\n\r\nHere are some practical examples of what you can do with **SocialVec**:\r\n\r\n- **Finding similar entities:** Retrieve universities similar to UC Berkeley based on the cosine similarity of their SocialVec embeddings.\r\n- **Recommending Twitter accounts:** Suggest accounts similar to those followed by a specific user, leveraging social context captured in the embeddings.\r\n- **Assessing political leaning:** Determine the political bias of news sources by comparing their similarity to embeddings of politically polarized accounts (e.g., accounts of prominent politicians).\r\n- **Exploring entity analogies:** Complete analogies like *\"X-Factor : Simon Cowell :: The Voice : ?\"* using vector arithmetic on SocialVec embeddings.\r\n\r\nAdvantages of SocialVec\r\n=======================\r\n\r\n- **Captures social world knowledge:** Unlike embeddings derived from factual knowledge bases like Wikipedia or Wikidata, SocialVec embeddings reflect relationships between entities based on social media interactions.\r\n- **Wider coverage:** SocialVec represents a broader range of entities, as many Twitter accounts do not have corresponding Wikipedia pages.\r\n\r\nNotes\r\n=====\r\n\r\nThis README covers the pre-trained embeddings provided by the package. Specific implementation details and additional functionality will be defined as part of the package's development.\r\n\r\nCredits\r\n=======\r\n\r\nThis package was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template.\r\n\r\n.. _Cookiecutter: https://github.com/audreyr/cookiecutter\r\n.. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage\r\n\r\n\r\nHistory\r\n-------\r\n\r\n0.1.0 (2022-09-29)\r\n------------------\r\n\r\n* First release on PyPI.\r\n\r\n0.1.1 (2022-09-29)\r\n------------------\r\n\r\n* Include config.yaml in the distribution.\r\n\r\n0.1.2 (2022-10-02)\r\n------------------\r\n\r\n* Rearrange config.yaml\r\n* Support multiple versions of the SocialVec model\r\n* Fix bug when searching for similarity using username\r\n\r\n0.1.3 (2022-10-14)\r\n------------------\r\n* Initial version of SocialVecClassifier\r\n\r\n0.1.4 (2022-11-08)\r\n------------------\r\n* Updates to SocialVecClassifier\r\n\r\n0.1.5 (2023-11-07)\r\n------------------\r\n* Update a dedicated model for the SocialVecClassifier (2020c)\r\n\r\n0.1.6 (2023-11-09)\r\n------------------\r\n* Modify requirements to support more up-to-date python versions\r\n\r\n0.1.7 (2024-10-22)\r\n------------------\r\n* Add the option to load the model to RAM in case there is no write permission to the package folder (which\r\n\r\n0.1.7.1 (2024-10-22)\r\n--------------------\r\n* Add pypi documentation\r\n",
"bugtrack_url": null,
"license": "MIT license",
"summary": "SocialVec is a framework of Social Embeddings for eliciting social world knowledge from social networks.",
"version": "0.1.7.1",
"project_urls": {
"Homepage": "https://github.com/nirlotan/socialvec"
},
"split_keywords": [
"socialvec"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "6509982a1fc4db1c2fc9a354d0d9de2a35d6ad4c4a411ad1701602bf3ab2fb4e",
"md5": "45f432abea4cd0d827d3c0c959d64513",
"sha256": "e3685526f89ed7d92d777cdc5f286c3c77363cd98fcb8eb14a107ed260bece7e"
},
"downloads": -1,
"filename": "socialvec-0.1.7.1-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "45f432abea4cd0d827d3c0c959d64513",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.8",
"size": 38998,
"upload_time": "2024-10-22T12:38:21",
"upload_time_iso_8601": "2024-10-22T12:38:21.222824Z",
"url": "https://files.pythonhosted.org/packages/65/09/982a1fc4db1c2fc9a354d0d9de2a35d6ad4c4a411ad1701602bf3ab2fb4e/socialvec-0.1.7.1-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "94fa9ae5c92a3d0d616ee5e1f723621e53c7ee4649d2e79ad977a92e1ad415c8",
"md5": "0f3354c091a1565fdf0038778be92b5c",
"sha256": "5349fa37c6b2bd5d4512d1bdbcebad856030116fd2e619d60294fb69de906d86"
},
"downloads": -1,
"filename": "socialvec-0.1.7.1.tar.gz",
"has_sig": false,
"md5_digest": "0f3354c091a1565fdf0038778be92b5c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 32252,
"upload_time": "2024-10-22T12:38:22",
"upload_time_iso_8601": "2024-10-22T12:38:22.935486Z",
"url": "https://files.pythonhosted.org/packages/94/fa/9ae5c92a3d0d616ee5e1f723621e53c7ee4649d2e79ad977a92e1ad415c8/socialvec-0.1.7.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-10-22 12:38:22",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "nirlotan",
"github_project": "socialvec",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"tox": true,
"lcname": "socialvec"
}
JSON
