JMIR Publications

ABSTRACT

Background:

Pain description is fundamental to healthcare. The McGill Pain Questionnaire (MPQ) has been validated as a tool for multidimensional measurement of pain, but its use relies heavily on language proficiency. The MPQ has also remained unchanged since its inception, yet the English language has evolved significantly since then. The advent of the internet and social media allows for generation of a staggering amount of publicly-available data, allowing linguistic analysis at a scale that has never been seen before.

Objective:

The objectives of this investigation were to use social media data to examine the relevance of pain descriptors from the existing MPQ, identify novel contemporary English descriptors for pain amongst users of social media, and suggest a modification for a new MPQ for future validation and testing.

Methods:

All posts from social media platforms from 1 January 2019 to 31 December 2019 were extracted. Artificial intelligence and emotion analytics algorithms (Crystalace and CrystalFeel) were used to measure the emotional properties of text, including “sarcasm”, “anger”, “fear”, “sadness”, “joy” and “valence”. Word2Vec was used to identify new pain descriptors associated with the original descriptors from the MPQ. Analysis of count and pain intensity formed the basis for proposing new pain descriptors, as well as determining the order of pain descriptors within each subclass.

Results:

118 new associated words were found via Word2Vec. 49 (41.5%) of these words had a count of at least 110, which corresponded to the count of the bottom 10% of the original MPQ pain descriptors. The count and intensity of pain descriptors were used to formulate the inclusions for a new pain questionnaire. For the suggested new pain questionnaire, 11 existing pain descriptors were removed, 13 new descriptors were added to existing subclasses, and a new “Psychological” subclass comprising 9 descriptors was added.

Conclusions:

The described methodology could be repeated at regular intervals to ensure the relevance of pain questionnaires. Count and intensity of words can be utilized for identification of suitable pain descriptors. The original MPQ is inadequate for reporting of the psychological aspect of pain.