Data mining is a process of extracting patterns or correlations from larger data sets that are used for analysis. My experience with data mining came from a past project in which I gathered the Inaugural Addresses of the presidents in order to extract common patterns within the speeches. That is where Orange comes in, as a useful and functional tool for those with different levels of comfortability when it comes to data mining, even a novice such as myself.

Orange is an open-source data mining, data analysis and visualization tool. Orange provides users with the ability to take large sets of data, plug them in, and generate different interactive visualizations. The tool uses “widgets” to create visualizations such as, heat maps, decision trees, scatter plots, among others. These visualizations allow the user to conduct exploratory analysis on their data sets.

A prime example of the versatility that Orange provides can be viewed through a recent blog from their own website. A workshop was held for archeologist to show them how to use Orange in their own work. Orange demonstrated that it could be used to generate what type of artefact they might come across based on data they had from images, in their own words, “predicting a type of the artefact from the image.” The multi-use, multi-faceted tool is beneficial not only to data experts but in a variety of different professions.

While it might be easier for someone with a background in data analysis to begin using Orange, data mining, visualizations and analysis are made accessible and understandable through their user-friendly guides and YouTube videos dedicated to teaching how Orange works.  

Download Orange here: 

Students and professors at Wheaton college worked for over a decade to create Lexos, a free and web-based text analysis tool. Lexos was created so that users could upload text collections from the web and extract patterns from the text in order to gather data and create visualizations. Lexos is a product of Wheaton college’s Lexomics program, which integrates traditional methods of text analysis, such as stylistic analysis, with computation methods of text analysis, such as vocabulary density and clustering analysis, better described as grouping similar texts together. As a result, Lexos has sought to help students and researchers to observe patterns within texts and visualize them for more in-depth analysis.

When opening up Lexos on your web-browser, you will see five different tabs: upload, manage, prepare, visualize, and analyze. Primarily, Lexos works well with small to medium-sized texts in ancient languages that don’t use Latin as their foundation such as Greek. Unique to Lexos that does not apply to other text analysis tools such as Voyant or Orange, is the ability to clean, organize, and finalize all in one interface. Whether it be students or researchers, Lexos provides an easy to navigate and friendly user layout that does not require additional training in order to use the tool. Users have the option to download Lexos locally to work on larger projects, or access through a browser, making it accessible in a few different ways. The newest version (2019) is updated and accessible to those looking for a text analysis tool to use.

Access the tool here:

Read more about Lexomics and Lexos here:

The South Carolina Moving Image Research Collections and the Interdisciplinary Mathematics Institute, both of the University of South Carolina, partnered with the National Endowment for the Humanities to make AEO-Light available to the public as an open source tool, allowing for audio attached to digitally scanned video and image files to be preserved. Since the initial project, AEO-Light 2.0 has been developed and is now available to the public. AEO-Light 2.0 can generate audio reliably from nearly any optical sound format and is now included in the Federal Agencies Digitization Guidelines Initiative’s specifications for preserving motion picture film materials.

Download the updated software here:

For more information go to:”>”>

Other information provided at:”>”>

To follow updates on the project:


Mukurtu (MOOK-oo-too) is a free, open-source content management system for digital heritage materials. The project was born from the needs of the Warumungu Aboriginal community who wanted an archival platform that allowed them to organize, manage and share their digital cultural heritage in their own way, on their own terms. For example, the Warumugu Aboriginal community observe cultural traditions that determine how they share their cultural materials and knowledge. Designed collaboratively by indigenous groups and academic researchers, the project empowers communities to share their cultural heritage online with their tales, knowledge and cultural artifacts. Mukurtu further allows these communities to organize, describe and share digital heritage within their communities in culturally appropriate ways. Mukurtu supports the unique needs of indigenous libraries, archives, and museums as they seek to preserve and share their digital heritage.

To learn more about Mukurtu CMS visit the following websites: