JMIR Publications

ABSTRACT

Background:

Cancer affects individuals, their family members, and friends, and increasingly, some of these individuals are turning to online cancer forums to express their thoughts/feelings and seek support such as asking cancer related questions. The thoughts/feelings expressed and the support needed from these online forums may differ depending on if: (i) an individual has or had cancer or (ii) an individual is a family member or friend of an individual who has or had cancer; the language used in posts in these forums may reflect these differences.

Objective:

Determine language differences in posts on an online cancer forum by: (i) users who self-declare to have or had cancer compared to (ii) users who self-declare to be family members or friends of individuals with or that had cancer.

Methods:

: Using a natural language processing algorithm, latent dirichlet allocation (LDA) and Linguistic Inquiry Word Count (LIWC), a psycholinguistic dictionary, we analyze posts published in an online cancer forum with the aim to delineate the language features associated with users in these different groups.

Results:

Users who self-declare to have or had cancer were more likely to post about LDA topics related to hospital visits (Cohen’s D=0.671) and use words associated with LIWC categories related to health (Cohen’s D=0.635) and anxiety (Cohen’s D=0.126). In contrast, users who declared to be family members or friends tend to post about LDA topics related to losing a family member (Cohen’s D=0.702) and the LIWC categories on focusing on the past (Cohen’s D = 0.465) and death (Cohen’s D = 0.181) were more associated with these users.

Conclusions:

Responders to online cancer forums need to be cognizant of these differences in language use by users with cancer compared to family members and friends of those with cancer. Using LDA and LIWC, we show that language features can delineate these groups allowing forum members to tailor their responses based on these findings.