iSA | R Documentation |
This function implements the iSA - integrated Sentiment Analysis algorihtm
iSA(Strain, Stest, Dtrain, nboot = 1000, predict = FALSE, ret.boot = FALSE, seqlen = 5, sparse = FALSE, verbose = TRUE, tolerance=Inf)
Strain |
a vector of stem strings belonging to the training set |
Stest |
a vector of stem strings belonging to the test set |
Dtrain |
a vector of codings belonging to the training set |
nboot |
number of bootstrap replications for standard error estimation |
predict |
non in use |
ret.boot |
return all bootstrap estimates? |
seqlen |
length of substrings used in iSA |
sparse |
use sparse matrix to store data? |
verbose |
show all steps? |
tolerance |
threshold for numerical determinant. Defaut = |
Prediction is implemented but only beta. Use it at your own risk.
est |
estimated parameters |
tab |
table of results |
best |
bootstrap estimated parameters |
btab |
table of results for bootstrap estimates |
pred |
prediction for each entry |
tim |
execution time |
Stefano M. Iacus
Iacus, S.M., Curini, L., Ceron, A. (2015) iSA (U.S. provisional patent application No. 62/215264) Ceron, A., Curini, L., Iacus, S.M. (2016) iSA: A fast, scalable and accurate algorithm for sentiment analysis of social media content, Information Sciences, V. 367-368, p. 105-124.
prep.data
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.