@article{wang-eisner-2018-tacl,

title = {Surface Statistics of an Unknown Language Indicate How 

 to Parse It},

author = {Dingquan Wang and Jason Eisner},

url = {http://cs.jhu.edu/~jason/papers/#wang-eisner-2018-tacl},

issn = {2307-387X},

journal = {Transactions of the Association for Computational 

 Linguistics (TACL)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Michael-J.-Paul:2016fpc,

title = {Assessing the validity of online drug forums as a source for estimating demographic and temporal trends in drug use},

author = {Michael J Paul and Margaret S Chisolm and Matthew W Johnson and Ryan G Vandrey and Mark Dredze},

journal = {Journal of Addiction Medicine},

volume = {10},

number = {5},

pages = {324--330},

abstract = {Objectives: Addiction researchers have begun monitoring online forums to uncover self-reported details about use and effects of emerging drugs. The use of such online data sources has not been validated against data from large epidemiological surveys. This study aimed to characterize and compare the demographic and temporal trends associated with drug use as reported in online forums and in a large epidemiological survey. Methods: Data were collected from the website, drugs-forum.com, from January 2007 through August 2012 (143,416 messages posted by 8,087 members) and from the United States National Survey on Drug Use and Health (NSDUH) from 2007-2012. Measures of forum participation levels were compared with and validated against two measures from the NSDUH survey data: percentage of people using the drug in last 30 days and percentage using the drug more than 100 times in the past year. Results: For established drugs (e.g., cannabis), significant correlations were found across demographic groups between drugs-forum.com and the NSDUH survey data, while weaker, non-significant correlations were found with temporal trends. Emerging drugs (e.g., Salvia divinorum) were strongly associated with male users in the forum, in agreement with survey-derived data, and had temporal patterns that increased in synchrony with poison control reports. Conclusions: These results offer the first assessment of online drug forums as a valid source for estimating demographic and temporal trends in drug use. The analyses suggest that online forums are a reliable source for estimation of demographic associations and early identification of emerging drugs, but a less reliable source for measurement of long-term temporal trends.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}