(This feature is only available in NVivo installations with coding enhancements enabled.)
Automatically detect and code sentiment
Quickly identify expressions of sentiment in your content using the Autocode Wizard. Autocode sentiment to find out Is the general tone of my content positive or negative?
Text analytics is a complex process—human perception of sentiment is always going to be more accurate.
The process
Select multiple files, codes or cases and use the Autocode Wizard to produce results. A coding matrix is created, and content is coded to sentiment codes.
Limitations of sentiment autocoding
NVivo searches for expressions of sentiment in the content.
It is important to understand that this tool does not classify content according to sentiment. It does not take each piece of content and rate it on a Likert sentiment scale. It looks at the sentiment of words in isolation—the context is not taken into account.
Like most text analysis tools, NVivo cannot recognize:
- sarcasm
- double negatives
- slang
- dialect variations
- idioms
- ambiguity
Sentiment scoring
The process uses a scoring system. Each word containing sentiment has a pre-defined score. Each sentiment code represents a range on a scale (of sentiment).
- The score for each word determines the sentiment code it is coded to.
- The score of words can change if they are preceded by a modifier (for example, more or somewhat) which intensifies the sentiment.
- Words with a score that fall within the neutral range are not coded.
Coding examples
Example 1 - Simple sentiment
In this example, the word safe has a score which falls within the moderately positive range, so it is coded to the sentiment code Moderately Positive.
Example 2 - Multiple words of the same sentiment
In this example, the word receptive has a score which falls within the moderately positive range, and the word significantly has a score which falls within the very positive range. When a sentence contains multiple positive or multiple negative words, the sentence is coded to the most extreme child code for that sentiment. In this example, the sentence is coded to the sentiment code Very Positive.
Example 3 - Both positive and negative sentiment
In this example, the word valuable has a score which falls within the moderately positive range, and the word dangerous has a score which falls within the moderately negative range. This sentence is coded to the sentiment code Moderately Positive and the sentiment code Moderately Negative.
Example 4 - Neutral sentiment
In this example, the word top has a sentiment score that falls within the neutral range on the scale—so the sentence is not coded to any sentiment code.
Example 5 - No sentiment
In this example, there is no sentiment detected in any word—so the sentence is not coded to any sentiment code.
Mixed sentiment coding
It's possible to have the same sentence coded to positive and negative sentiment codes—because the analysis process looks at words in isolation.
You can easily identify content coded to multiple codes by running a coding query.
When reviewing the results of this query, you might choose to uncode some of the references at one of the sentiment codes using coding stripes.
NVivo won't code the same content at multiple positive or multiple negative codes.
- In List View, select the codes, cases or text files you want to autocode. Text files include documents, PDFs, datasets and transcripts—they do not have to be of the same type but they should be the same language.
- On the Home tab, in the Coding group, click Autocode then follow the steps on the Wizard.
Wizard step | Description |
---|---|
Choose how you would like to autocode |
Click Identify sentiment. You may be prompted to download and install additional files. Make sure your project text content language is set to the language of the sources you are analyzing. |
Identifying sentiment |
NVivo analyzes your files for sentiment. |
Select how your text passages will be coded |
Choose how finely NVivo should code text passages:
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. |
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 coded by the Wizard.
2Rows display the files that have been coded by the Wizard.
3 Cells display the number of coding references that were created for a file (row) at a code (column). You can change the display, for example transpose the columns and rows—click Transpose in the View group, on the Matrix tab.
4 Click the Chart tab to see a visual representation of the autocoding results.
NOTE The number of coding references for a file displayed in the Codes column in List View includes the coding matrix.
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.
You can code and uncode in sentiment codes, include them in a framework matrix and review the references just like any other code.
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.
- 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.
- Decide whether you are satisfied with the results—do you want to keep the coding or undo the entire autocoding operation?
- If you are mostly satisfied with the results, but need to fine-tune some of the autocoding, you may want to uncode some of the references. Alternatively, you may want to change coding from one sentiment to another. The coding reference is still displayed in Detail View for the cell, even if you have uncoded or reassigned it.
- If you are not satisfied with the overall results, you may want to 'undo' the autocoding completely.
- Open each child sentiment code and change the sentiment coding if required.
- 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.
- Discover the general sentiment towards an issue by autocoding your files to themes then running a matrix coding query.
Change sentiment coding
- Open a child sentiment code in Detail View.
- Select the content you want to change.
- On the Sentiment tab, in the Coding group, click Change Sentiment then select the sentiment code you want the reference coded to. The selected content is uncoded from the current sentiment code and re-coded to the selected sentiment code.
NOTE
- Alternatively, you can right-click on the selected content and choose Change Sentiment.
- Select Neutral (Uncode) to remove the sentiment coding from the selected content.
Why am I getting unexpected results from sentiment coding?
Autocoding sentiment uses linguistic processes and a specialized sentiment dictionary 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. The autocoding themes process can only detect one language at a time—and this is based on the text content language setting of your project.
- 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.
How can I identify autocoded sentiment?
Autocoded sentiment references that were created by the Wizard are associated with the user profile 'NVivo' with the initials 'NV'.
If you have performed multiple sentiment autocoding operations, you will not be able to distinguish which references were created by a particular coding operation. To see the references from a particular operation, you can view the specific coding matrix in the Coding Matrices folder.
You can run a matrix coding query to display the coding references currently associated with the user 'NVivo'.