{
    "info": {
        "author": "Akshay Agrawal, Shane Leonard",
        "author_email": "akshayka@cs.stanford.edu, shanel@stanford.edu",
        "bugtrack_url": null,
        "classifiers": [
            "Development Status :: 3 - Alpha",
            "Intended Audience :: Developers",
            "License :: OSI Approved :: GNU General Public License v2 (GPLv2)",
            "Programming Language :: Python :: 2",
            "Programming Language :: Python :: 2.6",
            "Programming Language :: Python :: 2.7",
            "Topic :: Scientific/Engineering :: Artificial Intelligence"
        ],
        "description": "Classifying MOOC Discussion Forums\n==================================\n\nThe edxclassify package contains a classification suite built to\ndetect learner affect and behavior in the discussion forums of Massive\nOpen Online Courses (MOOCs). It is a result of a year's worth of research\nat Stanford and was designed to enable the discovery of insights into\nforums attached to Stanford's `online course\nofferings <https://lagunita.stanford.edu/>`_.\n\nResearch and Motivation\n------------------------\nOur motivation to discover insights into the dynamics of these courses is\nthree-fold. In particular, we wish to:\n\n1. better understand the educational and learning process,\n2. improve the educational environment for MOOC learners, and\n3. empower instructors by equipping them with a suite of tools designed to\n   ease the burden of teaching large-scale classes.\n\nFor example, we could use a classifier that detects confusion in forum posts\nto help us target automated learning interventions in courses. We have built\nsuch a prototype; to learn more, please refer to our\n`paper <http://debugmind.com/youedu.pdf>`_, published in the eighth conference\non Educational Data Mining.\n\nIncluded Classifiers\n---------------------\nThe abstractions in edxclassify are general enough to be applicable\nto most classification tasks. The repository does come packaged\nwith a set of classifiers that were trained to detect affect in Stanford's\nMOOC discussion forums. Since Stanford's courses are powered by edX, these\nclassifiers should be compatible with any edX MOOC; they should also be\ncompatible with other flavors of MOOCs, as their feature space is not\ntightly coupled with the particulars of edX.\n\nThese classifiers were trained\non subsets of the `Stanford MOOC-Posts\nDataset <http://datastage.stanford.edu/StanfordMoocPosts/>`_,\na collection of 30,000 human-tagged forum posts, originating from a\nvariety of courses. Classifiers to detect all six of the core variables\nin the MOOC-Posts Dataset -- confusion, urgency, sentiment, question,\nanswer, and opinion -- are included in this repository. The class\n``edxclassify.live_clf.LiveCLF`` provides an interface to them; see the module\n``edxclassify.live_clf`` for further documentation.\n\n\nRunning Experiments\n-------------------\n``edxclassify.harness`` is a driver that facilitates the training and testing of\nand experimentation with classifiers. After installation, it can be invoked\nwith the command ``clfharness``.\n\nData\n----\nThe MOOC-Posts Dataset is available to researchers,\n`upon request <http://datastage.stanford.edu/StanfordMoocPosts/>`_.\n\nMuch of the included code in edxclassify was designed for data formatted\nas per ``edxclassify.feature_spec``; in particular, the harness takes\ndata files each containing a pickled list of examples, each example a list\nwith features in the positions specified in ``edxclassify.feature_spec``.\nIf you would like access to these data files, first request access to the\nMOOC-Posts Dataset. When your request is approved, send an email to\nakshayka ~at~ cs.stanford.edu with subject line\n\"edxclassify: request for data files\".\n\nInstallation\n-------------\nInstallation can proceed in two ways: from source or from pip. Note that\nwhen installing from pip, only a subset of the pre-trained classifiers found\nin this repository will be included, due to size constraints imposed by pypi.\nIn particular, the pypi version only includes classifiers for confusion,\nwhereas the source version includes classifiers for all six MOOC-Posts\nvariables.\n\nRegardless of whether you install from source or from pip, begin by installing\n`scikit-learn <http://scikit-learn.org/dev/install.html>`_ and its\ndependencies; make sure to install version 0.15.2 to ensure compatibility with\nskll.\n\nIf installing from source, clone this repository and simply run\n``python setup.py install``. Otherwise, run ``pip install edxclassify``.",
        "description_content_type": null,
        "docs_url": null,
        "download_url": "UNKNOWN",
        "downloads": {
            "last_day": -1,
            "last_month": -1,
            "last_week": -1
        },
        "home_page": "https://github.com/akshayka/edxclassify",
        "keywords": "machine-learning classification education mooc moocs forum              discussion",
        "license": "GNU General Public License v2",
        "maintainer": null,
        "maintainer_email": null,
        "name": "edxclassify",
        "package_url": "https://pypi.org/project/edxclassify/",
        "platform": "UNKNOWN",
        "project_url": "https://pypi.org/project/edxclassify/",
        "project_urls": {
            "Download": "UNKNOWN",
            "Homepage": "https://github.com/akshayka/edxclassify"
        },
        "release_url": "https://pypi.org/project/edxclassify/0.10.a1/",
        "requires_dist": null,
        "requires_python": null,
        "summary": "A machine learning workflow with classifiers to detect                affect in MOOC discussion forums.",
        "version": "0.10.a1"
    },
    "last_serial": 1595407,
    "releases": {
        "0.10.a1": [
            {
                "comment_text": "",
                "digests": {
                    "md5": "6094fd27e37f5228fad99297427a9292",
                    "sha256": "5be53777a51abc22b81b2ef046399609781b56eb032b49c98fc4c6e350ccd9c2"
                },
                "downloads": -1,
                "filename": "edxclassify-0.10.a1.tar.gz",
                "has_sig": false,
                "md5_digest": "6094fd27e37f5228fad99297427a9292",
                "packagetype": "sdist",
                "python_version": "source",
                "requires_python": null,
                "size": 10707593,
                "upload_time": "2015-06-17T04:31:06",
                "url": "https://files.pythonhosted.org/packages/4e/98/bd147c431346fbe43274d97d49859d6dccf3408d44d5803fe7f29682dbf2/edxclassify-0.10.a1.tar.gz"
            }
        ]
    },
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "6094fd27e37f5228fad99297427a9292",
                "sha256": "5be53777a51abc22b81b2ef046399609781b56eb032b49c98fc4c6e350ccd9c2"
            },
            "downloads": -1,
            "filename": "edxclassify-0.10.a1.tar.gz",
            "has_sig": false,
            "md5_digest": "6094fd27e37f5228fad99297427a9292",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 10707593,
            "upload_time": "2015-06-17T04:31:06",
            "url": "https://files.pythonhosted.org/packages/4e/98/bd147c431346fbe43274d97d49859d6dccf3408d44d5803fe7f29682dbf2/edxclassify-0.10.a1.tar.gz"
        }
    ]
}