This work is part of a new initiative to use machine learning to identify online harassment in social media and comment streams. Online harassment goes underreported due to the reliance on humans to identify and report harassment, reporting that is further slowed by requirements to fill out forms providing context. In addition, the time for moderators to respond and apply human judgment can take days, but response times in terms of minutes are needed in the online context. Though some of the major social media companies have been doing proprietary work in automating the detection of harassment, there are few tools available for use by the public. In addition, the amount of labeled online harassment data and availability of cross platform online harassment datasets is limited. We present the methodology used to create a harassment dataset and classifier and the dataset used to help the system learn what harassment looks like.
head-the pain being mostly located over the right orbit. So great was the intolerance of light, that it was necessary to have it kept wholly excluded from the room. She continued in a similar condition, sometimes a little better and then again worse, until the 28th day of December,
The origin of the present paper may be traced to a request made to me by Dr. Cunningham, when I was passing through Florence in November 1896, to examine a list of the English and Scotch monasteries which furnished raw wool to the mediæval Florentine wool merchants, given in the fourteenth century manuscript of Balducci Pegolotti's ‘Pratica della Mercatura,’ preserved in the Riccardian Library. This list, as printed by Peruzzi in his ‘Storia del Commercio,’ was suspected by Dr. Cunningham to contain sundry clerical and other inaccuracies, a suspicion which proved to be amply justified in fact. It was then suggested to me that it might be worth while to try and collect information bearing upon the wool trades of the Florentine Republic as a whole, inasmuch as there must assuredly be no little material in the way of contemporary documents stored away in Florentine archives and libraries.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.