LightSide: Difference between revisions
Jump to navigation
Jump to search
(Created page with "{{Data mining and learning analytics tools |field_logo= |field_screenshot= |field_name=LightSide Researcher's Workbench |field_developers=Carnegie Mellon University’s Langua...") |
mNo edit summary |
||
(4 intermediate revisions by the same user not shown) | |||
Line 1: | Line 1: | ||
{{Data mining and learning analytics tools | {{Data mining and learning analytics tools | ||
|field_logo= | |field_logo=Lightside research title.png | ||
|field_screenshot= | |field_screenshot= | ||
|field_name=LightSide Researcher's Workbench | |field_name=LightSide Researcher's Workbench | ||
Line 12: | Line 12: | ||
|field_last_release= | |field_last_release= | ||
|field_last_version= | |field_last_version= | ||
|field_description= | |field_description={{quotation|The open-source LightSide platform, including the machine-learning and feature-extraction core as well as the researcher's workbench UI, has been and continues to be funded in part through Carnegie Mellon University, in particular by grants from the National Science Foundation and the Office of Naval Research.}} ([http://ankara.lti.cs.cmu.edu/side/ LightSide home page], sept. 2014). | ||
|field_analysis_orientation=General analysis | |field_analysis_orientation=General analysis | ||
|field_data_analysis_objective= | |field_data_analysis_objective= | ||
|field_mining_tool_type=Text mining | |field_mining_tool_type=Text mining | ||
|field_data_manipulation_type= | |field_data_manipulation_type=Data analysis | ||
|field_import_format= | |field_import_format= | ||
|field_export_format= | |field_export_format= | ||
|field_extraction_type= | |||
|field_data_transformation_capabilities= | |field_data_transformation_capabilities= | ||
|field_analysis_type=Data mining methods and algorithms | |||
|field_visualisation_type= | |field_visualisation_type= | ||
|field_visualisation_characteristic= | |field_visualisation_characteristic= | ||
|field_tool_usability= | |field_tool_usability=somewhat difficult to use | ||
|field_end_user_type=Researchers | |field_end_user_type=Researchers | ||
|field_statistics_level= | |field_statistics_level=Basic | ||
|field_programming_level= | |field_programming_level=Basic | ||
|field_system_engineering_level= | |field_system_engineering_level=Basic | ||
|field_data_mining_models_level=Medium | |field_data_mining_models_level=Medium | ||
|field_completion_level=Low | |field_completion_level=Low | ||
Line 34: | Line 36: | ||
* http://lightsidelabs.com/what/research/ | * http://lightsidelabs.com/what/research/ | ||
* https://bitbucket.org/lightsidelabs/lightside | * https://bitbucket.org/lightsidelabs/lightside | ||
'''Short how to''' | |||
Lightside is based on machine learning algorightms that can learn to extract features (e.g. tag text) based on training examples entered by humans. | |||
Below is a longer, slightly modified quote from the [http://ankara.lti.cs.cmu.edu/side/LightSide_Researchers_Manual.pdf Manual (feb 2014): | |||
{{quotation| LightSide is divided into a series of six tabs following the entire process of machine learning. In the first, '''Extract Features''', training documents are converted into feature tables. Next, in '''Restructure Plugins''', we have built several tools which allow users to manually adjust the resulting feature tables. In '''Build Model''', the third tab, modern algorithms are used to discover latent patterns in that feature table. The classifier that results is able to reproduce human annotation.}} | |||
{{quotation|The next three tabs allow users to explore those trained models and use them to annotate new data. In the fourth tab, '''Explore Results''', offers error analysis tools that allow researchers to understand what their models do well and why they fail in some cases. The fifth, '''Compare Results''', allows users to look at specific differences between two different trained models to understand both gaps in performance as a whole and individually. The final tab, '''Predict Labels''', allows us to use the resulting trained models to annotate new data that no humans have labeled.}} | |||
{{quotation|The simplest workflow, for those with basic machine learning needs, comes from the first and third tabs. In each case we progress from an input data structure to an output data structure: | |||
''Documents → Extract Features → Feature Table → Build Model → Trained Model''}} | |||
The training file is in CSV format. The first line contains the data fields, e.g. ''class'' and ''text''. Each row contains an example. | |||
'''Other products''': | '''Other products''': |