Automatically detect and code sentiment (NVivo 15 Mac)

NOTE  This feature is available starting with NVivo 15.4.0.

Quickly identify expressions of sentiment in your content using the AI based sentiment analysis to determine if the overall tone is positive or negative.
Note: This is a complex process—human perception of sentiment is always going to be more accurate.

The process

Select multiple text files and use the Analyze Sentiment option to analyse sentiments in your content. A coding matrix is created, and content is coded to sentiment codes.

Steps to automatically code sentiment

1. In List View, select the text files you want to autocode. Text files do not have to be of the same type, but they should be the same language.

2. Right-click and select Autocode -> Analyze Sentiment from the context menu.

   Note: Alternatively, you can access this option from the top ribbon by selecting Home -> Autocode -> Analyze Sentiment or from the top menu bar by selecting Home -> Autocode -> Analyze Sentiment.

3. If the Artificial Intelligence Terms of Use dialog is displayed, follow the steps below:

   1. Click the AI Terms of Use link in the dialog.

      Lumivero Artificial Intelligence Terms of Use page is displayed for you to read.

   2. Return to NVivo, check the confirmation check box.

   3. Click OK.

4. In the Analyze Sentiment dialog, choose how you would like to perform the analysis:

   • Code sentences if you want individual sentences to be coded.

   • Code paragraphs if you want entire paragraphs to be coded.

   

5. Click Analyze.

   The results are displayed as a coding matrix in Detail View—and saved in the Coding Matrices folder.

   The coding references are added to the codes in the Sentiment folder in the Coding group. Additionally, a hierarchy chart (Tree map) is displayed showing the sentiment coding patterns.

Work with the results of sentiment coding

When you autocode sentiment, the results are displayed as a coding matrix in Detail View and coding references are stored in the Sentiment codes. You can view the saved coding matrix later if you want a record of the coding performed by the Wizard at a particular date and time. This coding matrix is a static record that is not updated if you subsequently uncode some of the content.

1Columns display the names of the codes that have been autocoded.

2Rows display the files that have been autocoded.

3Cells display the number of coding references that were created for a file (row) at a code (column).

Additionally, a hierarchy chart (Tree Map) is also displayed showing the patterns in the sentiment coding.

How are sentiment codes different?

Sentiment codes behave differently to other codes in NVivo.

There are two parent sentiment codes: Positive and Negative. Each parent code has two child codes: Very and Moderately. Coding in the child codes aggregates to the parent by default.

Sentiment codes are created and used by NVivo. You cannot create, rename, move or merge sentiment codes.

By default, positive sentiment codes are assigned the color green, and negative sentiment codes are assigned the color red. You can change these at any time.

Next steps after sentiment coding

Review the results to confirm that you are satisfied with the autocoding before performing other actions in your project—so that you can adjust the coding if you need to.

1. Review what has been coded. Double click a cell in the matrix to see the content that was coded to the intersection of the file and code. Is the content relevant to that code? Take a look at other cells in the matrix.
2. Open each child sentiment code and change the sentiment coding if required.
3. Run a coding query to identify content that is coded to both a positive and negative code—for example, choose to find all content coded to the sentiment codes Very negative and Very positive. Review the results of the query. If you want to uncode content at one of the sentiment codes, the best approach is to remove coding using coding stripes.

Why am I getting unexpected results from sentiment coding?

Autocoding sentiment uses generative Artificial intelligence to scan your files to identify sentiment. This is a complex task—manual coding is always going to be more accurate.

• Understand the structure of your files—look for clear sentence and paragraph structure. If you choose to Code sentences, full stops are used to designate the end of sentences. Make sure that sentences in your files end with a full stop, including bulleted lists and text in table cells within a document. Any full stops used to designate an abbreviation will be interpreted as the end of a sentence.
• Make sure each file is in one language, and that you process files of the same language together.
• Minimize the presence of advertising or repeated content in your files. If you are working with web pages, capture only the main content on the page before importing into your project.
• Be aware that a great deal of content won't be coded to all. It may be deemed not to have any sentiment, or the sentiment may fall within the neutral range on the sentiment scale.