In the Explorer interface itself it is not currently possible to sort the individual texts by their sentiment. This was in a previous version of Explorer and will return soon. On the other hand, there is a workaround that can be used in the meantime.



First of all you must export your project as an Excel file. This is done by clicking save as > Excel file in the top left panel of the project's Explore screen. When this file is prepared and you have opened it, you will see the "summary" tab by default, showing you a similar overview of to what is visible when you are exploring your project in the graphical interface. If you click on the 'Data' tab (at the bottom of the screen), you will change to a different sheet, with the original texts of your dataset, one text per row of the spreadsheet. Scrolling to the right, you will see columns marking the text with 0 or 1 for topic membership, and further still to the right you will find sentiment scores for 8 different tonalities, including negativity and skepticism. Using the normal Excel functionality, you can then sort the texts by the values in these columns and thus see the texts which receive the highest scores for negativity or positivity, that is to say the most negative or skeptical texts according to the system's sentiment analysis, depending on which column you sort by.