This microservice was created as a result of the OpenReq project funded by the European Union Horizon 2020 Research and Innovation programme under grant agreement No 732463.
The goal of this microservice is to classify a list of app reviews as either a bug report or a feature request. The source code to get classified reviews (including data cleaning, machine learning feature extraction, and classification based on pre-trained models code that is necessary to perform these tasks is bundled in a single Docker container). The response of the microservice is a list of app reviews that now includes the class they belong to.
-
Docker (→ https://www.docker.com/)
-
SentiStrength (→ http://sentistrength.wlv.ac.uk/)
-
Stanford POS Tagger (→ https://nlp.stanford.edu/software/tagger.shtml)
ri-analytics-classification-google-play-review requires you to:
-
aquire the sentistrength library from http://sentistrength.wlv.ac.uk/
-
mount the SentiStrength.jar file in the Docker run environment (e.g., docker run --rm -d -v "<PATH_TO_SENTISTRENGTH>/SentiStrength.jar:/SentiStrength.jar")
-
aquire stanford-postagger-full-2016-10-31.zip and upload a zip file to google drive and set the Docker ARG GDRIVE_DL_LINK to Google Drive sharing ID (docker build --build-arg "GDRIVE_DL_LINK=<SHARE_ID>"). This will download and unzip the Stanford POS Tagger files from Google Drive.
Run the following commands to start the microservice:
1) docker build -t --build-arg "GDRIVE_DL_LINK=<SHARE_ID>" ri-analytics-classification-google-play-review . 2) docker run -v "<PATH_TO_SENTISTRENGTH>:/SentiStrength.jar" -p 9651:9651 ri-analytics-classification-google-play-review
The API is documented by using Swagger2:
See OpenReq project contribution Guidlines