EntityFinder Download and Help
Opinion mining has been an active research area in recent years. The task is to extract opinions expressed on entities and their attributes. For example, the sentence, "I love the picture quality of Sony cameras." expresses a positive opinion on the picture quality attribute of Sony cameras. Sony is the entity.
The program focuses on mining entities (e.g., Sony). This is an important problem because without knowing the entity, the extracted opinion is of little use.
The basic idea is based on the following paper.
"Entity Set Expansion in Opinion Documents". In Proceedings of the 22nd ACM Conference on Hypertext and Hypermedia (HT 2011)
1. Executable (.jar)
We only provide executable (*.jar) version of the system (without source). The program is not for commercial use.
2. Download and install
1). Download the program here
2). Unzip files to a directory. There are 3 files. "EntityFinder.jar" is the executable file. "sample_car.txt" is the sample file. "query.txt" is the query(seed) file.
3. How to use
java -jar EntityFinder.jar -i inputFile -q queryFile -o outputFile -s stopWordsFile [-Option value]
-i : represent input file.
-q : represent query file
-o: represent output file.
-s: represent stop-words file. this parameter is optional.
e.g. " java -jar EnityFinder.jar -i sample_car.txt -q query.txt -o output.txt"
4. Input format.
The input format for the input file should be as follows.
"Lower JJR the DT cost NN of IN the DT navigation NN system NN . ."
e.g. The word "cost" is followed by its corresponding Part of Speech (POS) tagging "NN".
5. Output format.
The output format for the output file is as follows.
The extracted features are ranked by importance. (please refer to the paper for details).
Last updated July 13, 2011