Analyzing Text Data

Properly acknowledging where data comes from is helpful for both the people who create the data and those who use it in scientific research.

For people who use the data, citing it means they can prove how they did their research and make it easier for other scientists to find and use the same data. It also makes the research more clear and helps improve the quality of the data. Plus, citing data encourages others to use it for their own research.

For people who make the data, citing it gives them the credit they deserve. It makes it easier for others to find their work, and it sets up some clear rules for recognizing data as an important part of scientific work. Additionally, citing data allows us to keep track of how influential the data is in the scientific community.

Citing data is very similar to citing journal articles, and many style manuals (APA, Chicago, MLA) offer guidance. At minimum, every data citation should include the following:

• Title
• Author
• Date 
• Version
• Persistent Identifier (e.g. DOI)
• Producer or Distributor (often the name of the repository managing the data, e.g. ICPSR or NCBI)

Persistent Identifiers are generally issued by the repository holding the data and include such identifiers as: Digital Object Identifier (DOI), Globally Unique Identifier (GUID), Archival Resource Key (ARK), Uniform Resource Name (URN), or any identifiers generally based on the Handel System.  URLs are not persistent identifiers but are okay to use in cases when no persistent identifier is provided. 

Examples:

Citation from ICPSR

Barnes, Samuel H. Italian Mass Election Survey, 1968. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 1992-02-16. https://doi.org/10.3886/ICPSR07953.v1

Schneider, Barbara, and Waite, Linda J. The 500 Family Study [1998-2000: United States]. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2008-06-03. https://doi.org/10.3886/ICPSR04549.v1

Federal Judicial Center. Judicial District Data Book, 1983: [United States]. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2006-01-18. https://doi.org/10.3886/ICPSR08439.v1

APA

ABC News. (2007). ABC News Education Poll, February 1990. (ICPSR version) [data file and codebook]. Radnor, PA: Chilton Research Services [producer]. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor]. doi:10.3886/ICPSR09440.v1

Chicago Style

ABC News. 2007. ABC News Education Poll, February 1990. ICPSR version. Radnor, PA: Chilton Research Services. Distributed by Ann Arbor, MI: Inter-university Consortium for Political and Social Research. doi:10.3886/ICPSR09440.v1.

MLA

ABC News. ABC News Education Poll, February 1990. ICPSR version. Radnor, PA: Chilton Research Services [producer]. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2007-01-26. Web. 11 Mar 2015. doi:10.3886/ICPSR09440.v1

This information has been adapted from the IASSIST Quick Guide to Data Citation and the MSU How to Cite Data Research Guide.

Most citation tools, such as RefWorks, Zotero, and Mendeley, do not currently have a template or "item type" for data citation. However, you can create one!

• Copy and paste the information from a recommended citation into a new Zotero item with the type "Document"
• Otherwise, use the "Document" item type to add the components of the citation

See the Citation Tools LibGuide for more information.