Location
Online
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2022 12:00 AM
End Date
7-1-2022 12:00 AM
Description
Social media platforms continue to play a leading role in the evolution of how people share and consume information. Information is no longer limited to updates from a user’s immediate social network but have expanded to an abstract network of feeds from across the global internet. Within the health domain, users rely on social media as a means for researching symptoms of illnesses and the myriad of therapies posted by others with similar implications. Whereas in the past, a single user may have received information from a limited number of local sources, now a user can subscribe to information feeds from around the globe and receive real-time updates on information important to their health. Yet how do users know that the information they are receiving is relevant or not? In this age of fake news and widespread disinformation the global domain of medical knowledge can be tough to navigate. Both legitimate and illegitimate practitioners leverage social media to spread information outside of their immediate network in order to reach, sway, and enlist a larger audience. In this research, we develop a system for determining the relevancy of linked webpages using a combination of web mining through Twitter hashtags and natural language processing (NLP).
Determining Link Relevancy in Tweets Related to Multiple Myeloma Using Natural Language Processing
Online
Social media platforms continue to play a leading role in the evolution of how people share and consume information. Information is no longer limited to updates from a user’s immediate social network but have expanded to an abstract network of feeds from across the global internet. Within the health domain, users rely on social media as a means for researching symptoms of illnesses and the myriad of therapies posted by others with similar implications. Whereas in the past, a single user may have received information from a limited number of local sources, now a user can subscribe to information feeds from around the globe and receive real-time updates on information important to their health. Yet how do users know that the information they are receiving is relevant or not? In this age of fake news and widespread disinformation the global domain of medical knowledge can be tough to navigate. Both legitimate and illegitimate practitioners leverage social media to spread information outside of their immediate network in order to reach, sway, and enlist a larger audience. In this research, we develop a system for determining the relevancy of linked webpages using a combination of web mining through Twitter hashtags and natural language processing (NLP).
https://aisel.aisnet.org/hicss-55/dsm/data_mining/3