Her categories in our study. SCLIWC specificity was greater than 0.70 for most of those categories except constructive emotion (.69) and discrepancy (.67). In Study 1, through correlation analysis among human ratings and SCLIWC variables of word count as these did in preceding research [7,27], we discovered considerable correlations together with the coefficients of typically precisely the same level in these studies. If using status count scoring technique in calculating SCLIWC variables on Weibo statuses, the correlation coefficients might be even higher. In Study 2, the evaluating based on signal-detection theory showed higher sensitivity of SCLIWC for several categories and higher specificity at the same time as adverse predictive value for most categories. The validities on various LIWC categories were of massive variations, as in Pennebaker et al.’s reports [28]. The distinction on both content and style of the 3 Web text types had been also reflected in our final results, in both the word percentage profiles also as the correlations amongst human ratings and SCLIWC variables. The discrepancies of word percentage profiles were constant with our prevalent sense about these text kinds, buy BMS-214662 though the discrepancies from the correlation coefficients may perhaps provide some guidelines in application, that there exists some difference of SCLIWC validity on various types of Internet text. As an example, the accuracies of detecting expressions of affective processes applying SCLIWC on Weibo statuses, Renren blogs and news comments were rather close, even though the lexicon seemed to carry out superior in detecting concerned contents in Renren blogs and news comments.How to PubMed ID:http://www.ncbi.nlm.nih.gov/pubmed/21187425 use SCLIWC to detect psychological expression in SNS brief net texts far more efficientlyOur second query, that how you can use SCLIWC in a far more effective method to detect psychological expressions on SNS quick text, was explored in two elements: the volume of texts along with the scoring approach. The earlier research relating to LIWC validity normally used written materials with aPLOS 1 | DOI:ten.1371/journal.pone.0157947 June 20,10 /Evaluating the Validity of Simplified Chinese LIWCsubstantial amount of words, including essays of individual writing [7] or messages in onlinebased assistance groups [27,29]. Though it might not be formally discussed before, it is uncomplicated to understand that the instruments based on lexicons, for instance LIWC, could carry out far better when the words inside the material attain or exceed a particular quantity. We found that SCLIWC could efficiently detect psychological expressions (medium to higher correlations with human ratings) of various categories, even when the material limited to a single day’s Weibo statuses (about 75?00 words on typical), and because the amount of statuses growing to a week’s in addition to a month’s, SCLIWC might be valid on far more categories. In addition to counting words, the usual way of processing texts with LIWC, counting statuses may very well be yet another solution when processing a set of Weibo statuses. As in our final results, the status count score commonly had larger correlations with human ratings on a day/week/month’s Weibo statuses, than the word count score had. In particular for the results on a month’s statuses, the correlations in between status count score and human ratings have been important on all chosen categories, which indicated that the status count scoring method was a really efficient processing process though employing SCLIWC to detect psychological expressions from a set of SNS quick texts. There is an essential difference amongst a set of SNS brief texts and most supplies pro.
