Last active
October 1, 2017 10:01
-
-
Save divanvisagie/fbbe38ee0d45acdc423ab46366a31937 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def sentimentCounter(list: List[String]): List[Int] = { | |
list.foldLeft(List[Int](0, 0, 0))((acc, item) => { | |
item match { | |
case "Positive" => List(acc.head + 1, acc(1), acc(2)) | |
case "Very positive" => List(acc.head + 2, acc(1), acc(2)) | |
case "Negative" => List(acc.head, acc(1) + 1, acc(2)) | |
case _ => List(acc.head, acc(1), acc(2) + 1) | |
} | |
}) | |
} | |
def analyzeWithCoreNLP(text: String): Double = { | |
if (text.isEmpty) return 0.0 | |
val props = new Properties() | |
props.setProperty("annotators","tokenize, ssplit, pos, lemma, parse, sentiment") | |
val pipeline = new StanfordCoreNLP(props) | |
val annotation = pipeline.process(text) | |
val sentences = annotation.get(classOf[CoreAnnotations.SentencesAnnotation]) | |
val sentimentStringValuesBuf = scala.collection.mutable.ArrayBuffer.empty[String] | |
sentences.forEach { sentence => | |
val sentiment = sentence.get(classOf[SentimentCoreAnnotations.SentimentClass]) | |
sentimentStringValuesBuf += sentiment | |
} | |
indexOfHighest(sentimentCounter(sentimentStringValuesBuf.toList)) match { | |
case 0 => 1.0 | |
case 1 => -1.0 | |
case 2 => 0.0 | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment