{ "info": { "author": "ASReview Core Development Team", "author_email": "asreview@uu.nl", "bugtrack_url": null, "classifiers": [ "Development Status :: 3 - Alpha", "License :: OSI Approved :: MIT License", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.6", "Programming Language :: Python :: 3.7" ], "description": "# Automated Systematic Review\n\n[![Build Status](https://travis-ci.com/msdslab/automated-systematic-review.svg?branch=master)](https://travis-ci.com/msdslab/automated-systematic-review) [![Documentation Status](https://readthedocs.org/projects/asreview/badge/?version=latest)](https://asreview.readthedocs.io/en/latest/?badge=latest) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3345593.svg)](https://doi.org/10.5281/zenodo.3345593)\n\n\n\n--- \n\n*This project is work in progress and **not** production ready.*\n\n---\n\nSystematic Reviews are \u201ctop of the bill\u201d in research. The number of systematic\nreviews published by researchers increases year after year. But performing a\nsound systematic review is a time-consuming and sometimes boring task. Our\nsoftware is designed to accelerate the step of screening abstracts and titles\nwith a minimum of papers to be read by a human with no or very few false negatives.\n\nOur Automated Systematic Review (ASR) software implements an oracle and a\nsimulation mode.\n\n- **Oracle** The oracle modus is used to perform a systematic review with\n interaction by the reviewer (the 'oracle' in literature on active learning).\n The software presents papers to the reviewer, whereafter the reviewer classifies them.\n- **Simulate** The simulation modus is used to measure the performance of our\n software on existing systematic reviews. The software shows how many\n papers you could have potentially skipped during the systematic review.\n\nThe full documentation is available at [https://asreview.readthedocs.io](https://asreview.readthedocs.io)\n\nThis Automatic Systematic Review software is being developed as part of a\nresearch project. This research project consists of multiple repositories. The\nfollowing respositories are (or will become) publicly available:\n\n- [automated-systematic-review-datasets](https://github.com/msdslab/automated-systematic-review-datasets) A project for collection, preprocessing and publication of systematic review datasets. The project describes the data storage format used by the software.\n- [automated-systematic-review-simulations](https://github.com/msdslab/automated-systematic-review-simulations) A repository with scripts for a simulation study and scripts for the aggregation and visualisation of the results.\n\n\n## Table of Contents\n\n* [Automated Systematic Review](#automated-systematic-review)\n* [Table of Contents](#table-of-contents)\n* [Active Learning for reviewing papers](#active-learning-for-reviewing-papers)\n* [Installation](#installation)\n* [Quick start](#quick-start)\n* [Tech](#tech)\n* [Datasets](#datasets)\n* [Frequently Asked Questions](#frequently-asked-questions)\n* [Publications](#publications)\n* [Citation](#citation)\n* [Contact and contributors](#contact-and-contributors)\n\n## Active Learning for reviewing papers\n\nThe ASR project implements learning algorithms that interactively query the\nresearcher. This way of interactive training is known as\n[Active Learning](https://en.wikipedia.org/wiki/Active_learning_(machine_learning)).\nThe ASR software offers support for classical learning algorithms and\nstate-of-the-art learning algorithms like neural networks. The following image\ngives an overview of the process.\n\n![Active Learning for reviewing papers](https://github.com/msdslab/automated-systematic-review/blob/master/images/deepreview.png?raw=true)\n\n\n## Installation\n\nThe ASR software requires Python 3.6+. The project is available on Pypi. Install the \nproject with:\n\n```bash \npip install asreview\n```\n\nInstall the development version of the Automated Systematic Review project directly \nfrom this Github page. One can do this with pip and git.\n\n``` bash\npip install git+https://github.com/msdslab/automated-systematic-review.git\n```\n\n## Quick start\n\nThe quickest way to start using the Automated Systematic Review (ASR) software is\nthe Command Line Interface (CLI). \nStart an interactive systematic review (Oracle mode) with the following line in CMD or shell:\n\n``` sh\nasreview oracle YOUR_DATA.csv --prior_included 29 181 379 2001 3928 3929 4547 --log_file results.log\n```\n\nExample output:\n\n```\nStart review in 'oracle' mode.\nPrepare dataset.\nStart with the Systematic Review.\n\nAnnual research review: The experience of youth with political conflict -\nChallenging notions of resilience and encouraging research refinement\nBarber, B. K.\n\nAims and method Drawing on empirical studies and literature reviews, this\npaper aims to clarify and qualify the relevance of resilience to youth\n...\nAuthors. Journal of Child Psychology and Psychiatry \u00a9 2013 Association for\nChild and Adolescent Mental Health.\n\nInclude [1] or exclude [0]:\n```\n\nThis command (`asreview oracle`) runs the software in oracle mode on the \n`YOUR_DATA.csv` dataset. Passing `prior_included` signifies the paper IDs\nthat should definitely be included, while `prior_excluded` are IDs of papers\nthat are definitely excluded. The higher the number of included/excluded papers,\nthe quicker the ASR software will understand your choices for inclusion.\nThe IDs are the idententifiers of papers, starting from\n0 for the first paper found in the dataset.\n\nTo benchmark an already executed review, use the simulation modus (`asreview simulation`).\nThe dataset then needs an additional column (\"label_included\") to signify their inclusion\nin the final review. The command for the simulation modus is similar to the oracle\nmode:\n\n``` sh\nasreview simulate YOUR_DATA.csv --prior_included 29 181 379 2001 3928 3929 4547 \\\n --prior_excluded 31 90 892 3898 3989 4390 --log_file results.log\n```\n\n## Tech\n\nThere are many different [models](https://asreview.readthedocs.io/en/latest/models.html), [query strategies](https://asreview.readthedocs.io/en/latest/query_strategies.html),\nand [rebalancing strategies](https://asreview.readthedocs.io/en/latest/balance_strategies.html) available. \nA LSTM neural network based model is currently the best performing and optimized. \nBy default, the ASR software will use models tuned on datasets available to us.\nTuning of models, query strategies and rebalanceing strategies is possible either\nthrough the CLI or the API.\n\n## Datasets\n\nThe ASR software accepts datasets in the RIS and CSV file format. [RIS\nfiles](https://en.wikipedia.org/wiki/RIS_(file_format)) are used by digital\nlibraries, such as IEEE Xplore, Scopus and ScienceDirect. Citation managers\nMendeley and EndNote support the RIS format as well. For simulation, we use an\nadditional RIS tag with the letters `LI`. For CSV files, the software accepts\na set of predetermined labels in line with the ones used in RIS files. Please\nsee the project [Automatic Systematic Review\nDatasets](https://github.com/msdslab/automated-systematic-review-datasets) for\nthe complete standard.\n\n## Frequently Asked Questions\n\n### Unknown command \"asreview\" on command line or terminal\n\nIn some situations, the entry point \"asreview\" can not be found after\ninstallation. First check whether the package is correctly installed. Do this\nwith the command `python -m asreview -h`. If this shows a decription of the\nprogram, please use `python -m` in front of all your commands. For example \n\n```\npython -m asreview oracle yourfile.csv\n```\n\n### How do I work with the Command Line?\n\nMacOS and Linux users can learn about bash on the website\n[programminghistorian.org](https://programminghistorian.org/en/lessons/intro-to-bash).\nWindows users may also follow this tutorial, but might prefer a tutorial on\n`cmd.exe`.\n\n## Publications\n\n- Dutch newspaper NRC on this project [\"Software vist de beste artikelen uit een bibliotheek van duizenden.\"](https://www.nrc.nl/nieuws/2019/01/14/software-vist-de-beste-artikelen-eruit-a3628952)\n- News site of Utrecht University: [\"A digital tracker dog for datasets\"\n](https://www.dub.uu.nl/en/depth/digital-tracker-dog-datasets)\n\n\n## Citation\n\nA research paper is coming up for this project. In the mean time, it can be cited with (fill in x and y for the version number):\n\n```\nASReview Core Development Team (2019). ASReview: Software for automated systematic reviews [version 0.x.y]. Utrecht University, Utrecht, The Netherlands. Available at https://github.com/msdslab/automated-systematic-review.\n```\n\nBibTeX:\n\n```bibtex\n@Manual{,\n title = {ASReview: Software for automated systematic reviews},\n author = {{ASReview Core Development Team}},\n organization = {Utrecht University},\n address = {Utrecht, The Netherlands},\n year = 2019,\n url = {https://pypi.org/project/asreview/}\n} \n```\n\n\n## Contact and contributors\n\nThis project is part of the research work conducted by the [Department of\nMethodology & Statistics](https://www.uu.nl/en/organisation/faculty-of-social-and-behavioural-sciences/about-the-faculty/departments/methodology-statistics), Faculty of Social and Behavioral Sciences, Utrecht\nUniversity, The Netherlands in collaboration with [Utrecht Applied Data Science](https://www.uu.nl/en/research/applied-data-science), \n[Information and Technology Services](https://www.uu.nl/en/organisation/information-and-technology-services-its), and [Utrecht University Library](https://www.uu.nl/en/university-library).\n\nFor any questions or remarks, please send an email to asreview@uu.nl.\n\n**Coordination**\n- [Rens van de Schoot](https://www.rensvandeschoot.com) (Main coordinator, [@Rensvandeschoot](https://github.com/Rensvandeschoot))\n- [Daniel Oberski](https://www.uu.nl/staff/DLOberski) (Scientific Director, [@daob](https://github.com/daob))\n\n**Engineers** \n- [Jonathan de Bruin](https://www.uu.nl/staff/JdeBruin1) (Lead engineer, [@J535D165](https://github.com/J535D165))\n- [Parisa Zahedi](https://www.linkedin.com/in/parisa-zahedi-28b17148/) ([@parisa-zahedi](https://github.com/parisa-zahedi))\n- Raoul Schram ([@qubixes](https://github.com/qubixes))\n- [Kees van Eijden](https://www.uu.nl/staff/CJvanEijden) ([@KvEijden](https://github.com/KvEijden))\n\n**Librarians**\n- [Jan de Boer](https://www.uu.nl/staff/JdeBoer) \n- [Edu Hackenitz](https://www.uu.nl/staff/EJMHackenitz)\n- [Felix Weijdema](https://www.uu.nl/staff/FPWeijdema)\n- [Bianca Kramer](https://www.uu.nl/staff/BMRKramer) \n\n**Affiliated Researchers**\n- [Pim Huijnen](https://www.uu.nl/staff/PHuijnen) (Digital Cultural History at the Department of History and Art History)\n- [Lars Tummers](https://www.uu.nl/staff/LGTummers) (Public Management and Behavior at Utrecht University, School of Governance)\n\n**Students**\n- [Gerbrich Ferdinands](https://www.linkedin.com/in/gerbrich-ferdinands-a21838b8) ([@GerbrichFerdinands](https://github.com/GerbrichFerdinands))\n- [Qixiang Fang](https://www.uu.nl/staff/QFang) ([@fqixiang](https://github.com/fqixiang))\n- Albert Harkema ([@sasafrass](https://github.com/sasafrass))\n\n\n", "description_content_type": "text/markdown", "docs_url": null, "download_url": "", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/msdslab/automated-systematic-review", "keywords": "systematic review", "license": "", "maintainer": "", "maintainer_email": "", "name": "asreview", "package_url": "https://pypi.org/project/asreview/", "platform": "", "project_url": "https://pypi.org/project/asreview/", "project_urls": { "Bug Reports": "https://github.com/msdslab/automated-systematic-review/issues", "Homepage": "https://github.com/msdslab/automated-systematic-review", "Source": "https://github.com/msdslab/automated-systematic-review/" }, "release_url": "https://pypi.org/project/asreview/0.2.1/", "requires_dist": [ "numpy", "tensorflow", "sklearn", "pandas", "modAL", "RISparser", "dill", "check-manifest ; extra == 'dev'", "coverage ; extra == 'test'" ], "requires_python": "", "summary": "Automated Systematic Review", "version": "0.2.1" }, "last_serial": 5982529, "releases": { "0.0.4": [ { "comment_text": "", "digests": { "md5": "6ddb3932b19305fda690d4dca2b96d66", "sha256": "99af9913718f990dbdeb3d2a7598d19c5935c3e2d101845524ba1d21fc404d7c" }, "downloads": -1, "filename": "asreview-0.0.4-py3-none-any.whl", "has_sig": false, "md5_digest": "6ddb3932b19305fda690d4dca2b96d66", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 41970, "upload_time": "2019-06-24T13:58:41", "url": "https://files.pythonhosted.org/packages/66/61/bf1db74918c431d868ceb7ef741f6115f372945a0dd062e0a97b88e63898/asreview-0.0.4-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "daf639f96cc58b16f58510224a1ca485", "sha256": "ff95ac9f8fea64d81af38bba3719c53b251ef8f7bfdaf7700d8187f2e43cef9a" }, "downloads": -1, "filename": "asreview-0.0.4.tar.gz", "has_sig": false, "md5_digest": "daf639f96cc58b16f58510224a1ca485", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 49032, "upload_time": "2019-06-24T13:58:43", "url": "https://files.pythonhosted.org/packages/54/ae/a0c2734ca3c86f331c47ab5dbba7b0c0d824c246644443cc413ebf5fc717/asreview-0.0.4.tar.gz" } ], "0.0.5": [ { "comment_text": "", "digests": { "md5": "9912ea70d3229910873ef4fc2accf024", "sha256": "2b29f3b995a285c7bfd305348134fe692bc496fbc5252778d5b31b86359451a4" }, "downloads": -1, "filename": "asreview-0.0.5-py3-none-any.whl", "has_sig": false, "md5_digest": "9912ea70d3229910873ef4fc2accf024", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 41705, "upload_time": "2019-06-24T14:46:34", "url": "https://files.pythonhosted.org/packages/4a/4c/714bd1376be2a3b96a9db615ae19111693f6da0676f358478e7ef00d7005/asreview-0.0.5-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "5fbe49f64a7195e686102b15ce7d1cc8", "sha256": "7715a2ccf5d60259dfc39da20facc490d8b1e16fd0839e055849cc957a0e3fd4" }, "downloads": -1, "filename": "asreview-0.0.5.tar.gz", "has_sig": false, "md5_digest": "5fbe49f64a7195e686102b15ce7d1cc8", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 46627, "upload_time": "2019-06-24T14:46:36", "url": "https://files.pythonhosted.org/packages/b0/d8/313cd25b372ea715987e82e74c74dbd4672a2d97fdada5f7259569f3f713/asreview-0.0.5.tar.gz" } ], "0.1.0": [ { "comment_text": "", "digests": { "md5": "258930fadaf43775ca9fd95d49ed5257", "sha256": "897a4ba51d27975fde9d898a2729bce50bc1a30f280db83cb50719be7c54b603" }, "downloads": -1, "filename": "asreview-0.1.0-py3-none-any.whl", "has_sig": false, "md5_digest": "258930fadaf43775ca9fd95d49ed5257", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 73811, "upload_time": "2019-07-22T09:18:58", "url": "https://files.pythonhosted.org/packages/f7/14/824fda2cf27390d35edd95675e5757bbc8a5caec03f41d6155610f98ccb1/asreview-0.1.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "84a587c3a0c5f9373ecf73c02cdb705e", "sha256": "4c5ddd61e91f47edcf3fc17ddb4e06f1da1ab860ff2f47e27aa3f8ab6f251da3" }, "downloads": -1, "filename": "asreview-0.1.0.tar.gz", "has_sig": false, "md5_digest": "84a587c3a0c5f9373ecf73c02cdb705e", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 45936, "upload_time": "2019-07-22T09:18:59", "url": "https://files.pythonhosted.org/packages/2d/be/30d59085354e6187772ff8951ddc7e964c65b5ec5c3405ab674b7afcde5e/asreview-0.1.0.tar.gz" } ], "0.1.1": [ { "comment_text": "", "digests": { "md5": "cc397d4ca21eed2a183a9195f896fb43", "sha256": "517c9d8289bdb244226dfcba81130b84685a4e1641c92c45dc914bce74d04404" }, "downloads": -1, "filename": "asreview-0.1.1-py3-none-any.whl", "has_sig": false, "md5_digest": "cc397d4ca21eed2a183a9195f896fb43", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 73803, "upload_time": "2019-07-22T09:53:25", "url": "https://files.pythonhosted.org/packages/1c/34/659c34d02c11642e4da01820ea82f999fcf21b08ee84a32dd0411f708657/asreview-0.1.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "6a4de848b727a4b0b039183c5a8822ac", "sha256": "8be5cbb34cd4b9e187cbc9a6b001879e0d3cea3a341474340a7c5129360ca41a" }, "downloads": -1, "filename": "asreview-0.1.1.tar.gz", "has_sig": false, "md5_digest": "6a4de848b727a4b0b039183c5a8822ac", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 46040, "upload_time": "2019-07-22T09:53:27", "url": "https://files.pythonhosted.org/packages/6e/25/43a9c4adc826a68140942511feb2d58a1e2997b1e6d5b169563c7b493840/asreview-0.1.1.tar.gz" } ], "0.2.0": [ { "comment_text": "", "digests": { "md5": "f7f8dba306ddb231a483ae606f7631e9", "sha256": "f46052736fe11dc242d05cd5b9154ea20e5d01c2d98fb63962450c7eeaecebe5" }, "downloads": -1, "filename": "asreview-0.2.0-py3-none-any.whl", "has_sig": false, "md5_digest": "f7f8dba306ddb231a483ae606f7631e9", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 54051, "upload_time": "2019-10-14T14:12:52", "url": "https://files.pythonhosted.org/packages/f4/87/49076799c4650650d69d95688c836ce65a17938947e9012e22f37b455ef8/asreview-0.2.0-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "bb04bae1854b04692e2618bd8ed12225", "sha256": "ca50ba74d5a00fc35c44808eb18aecc9c368749a597a1dc1589b51db45f6d0fe" }, "downloads": -1, "filename": "asreview-0.2.0.tar.gz", "has_sig": false, "md5_digest": "bb04bae1854b04692e2618bd8ed12225", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 57743, "upload_time": "2019-10-14T14:12:54", "url": "https://files.pythonhosted.org/packages/eb/aa/2956d257f9bb6f6875e6b0739f929d3cb9dc09779d0a816af636434024d8/asreview-0.2.0.tar.gz" } ], "0.2.1": [ { "comment_text": "", "digests": { "md5": "2fbe3b22848c981fc9b1dfaa0fd38cc2", "sha256": "7115fde76f9d9c101dd4c487ce294c64e3d36e0cfb89bab84bbb349c1e66f9c4" }, "downloads": -1, "filename": "asreview-0.2.1-py3-none-any.whl", "has_sig": false, "md5_digest": "2fbe3b22848c981fc9b1dfaa0fd38cc2", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 56948, "upload_time": "2019-10-16T10:55:11", "url": "https://files.pythonhosted.org/packages/84/0c/e4c3e030f5da6b802ba332ac1dff51d216e08ff9bf9b0601e88607105064/asreview-0.2.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "d7b419d3fae9c1b6c6836c62e03bdab3", "sha256": "1d81a8f925c7721732a3e9da48cb8cbbecc521d2e025bd6e1d49206402ad8f48" }, "downloads": -1, "filename": "asreview-0.2.1.tar.gz", "has_sig": false, "md5_digest": "d7b419d3fae9c1b6c6836c62e03bdab3", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 58449, "upload_time": "2019-10-16T10:55:14", "url": "https://files.pythonhosted.org/packages/c0/81/469eb98a93d54764e7640abf39fc1ed0613a267bb209ff8a00f7bae98665/asreview-0.2.1.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "2fbe3b22848c981fc9b1dfaa0fd38cc2", "sha256": "7115fde76f9d9c101dd4c487ce294c64e3d36e0cfb89bab84bbb349c1e66f9c4" }, "downloads": -1, "filename": "asreview-0.2.1-py3-none-any.whl", "has_sig": false, "md5_digest": "2fbe3b22848c981fc9b1dfaa0fd38cc2", "packagetype": "bdist_wheel", "python_version": "py3", "requires_python": null, "size": 56948, "upload_time": "2019-10-16T10:55:11", "url": "https://files.pythonhosted.org/packages/84/0c/e4c3e030f5da6b802ba332ac1dff51d216e08ff9bf9b0601e88607105064/asreview-0.2.1-py3-none-any.whl" }, { "comment_text": "", "digests": { "md5": "d7b419d3fae9c1b6c6836c62e03bdab3", "sha256": "1d81a8f925c7721732a3e9da48cb8cbbecc521d2e025bd6e1d49206402ad8f48" }, "downloads": -1, "filename": "asreview-0.2.1.tar.gz", "has_sig": false, "md5_digest": "d7b419d3fae9c1b6c6836c62e03bdab3", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 58449, "upload_time": "2019-10-16T10:55:14", "url": "https://files.pythonhosted.org/packages/c0/81/469eb98a93d54764e7640abf39fc1ed0613a267bb209ff8a00f7bae98665/asreview-0.2.1.tar.gz" } ] }