An insight analysis and detection of drug-abuse risk behavior on Twitter with self-taught deep learning

Computational Social Networks

Table 3 Most frequent Hashtags in positive tweets and negative tweets

Positive tweets	#weed, #smoke, #cannabis, #marijuana, #glassofig, #scientificglass, #WeedFirm, #maryjane, #dabs, #kush, #3wordsbetterthanIloveyou, #MarijuanaFunFacts, #pot, #dank, #high, #thc, #stoner, #blunt, #highlife, #AcademyAward, #OscarNominations, #ganja, #waterpipes, #np, #herblife
Negative tweets	#job, #snow, #hiring, #photo, #traffic, #CareerArc, #NBAVote, #Simon, #winter, #jobs, #Hospitality, #peace, #WomensMarch, #love, #Toronto, #Trump, #STAR, #nowplaying, #Orlando, #AZ, #np, #Veterans, #Retail, #SoundCloud, #nyc, #Inauguration, #cat, #weather, #MAGA