Java を使用したセンチメント分析に基づくインテリジェントなテキスト分類システムを作成する方法

// 加载训练数据
DataSource source = new DataSource("train.arff");
Instances train = source.getDataSet();
train.setClassIndex(train.numAttributes()-1);

// 构建模型
BayesNet classifier = new BayesNet();
classifier.buildClassifier(train);

// 保存模型
ObjectOutputStream oos = new ObjectOutputStream(
new FileOutputStream("model.bin"));
oos.writeObject(classifier);
oos.flush();
oos.close();

// 加载模型
ObjectInputStream ois = new ObjectInputStream(
new FileInputStream("model.bin"));
BayesNet classifier = (BayesNet) ois.readObject();

// 构建待分类的实例
Instance instance = new DenseInstance(2);
instance.setValue(0, "这个电影真是太好看了！");
instance.setValue(1, "正片太赞，恶评都是骗点击的！");

// 进行分类
double label = classifier.classifyInstance(instance);
System.out.println("分类标签：" + train.classAttribute().value((int)label));

mvn archetype:generate -DgroupId=com.example -DartifactId=myproject -DarchetypeArtifactId=maven-archetype-quickstart -DinteractiveMode=false

@RestController
public class SentimentAnalysisController {

  private BayesNet classifier;

  public SentimentAnalysisController() {
    // 加载模型
    try {
      ObjectInputStream ois = new ObjectInputStream(
        new FileInputStream("model.bin"));
      classifier = (BayesNet) ois.readObject();
      ois.close();
    } catch (IOException | ClassNotFoundException e) {
      e.printStackTrace();
    }
  }

  @PostMapping("/predict")
  public String predict(@RequestBody Map<String, String> reqBody) {
    String text = reqBody.get("text"); // 获取待分类的文本
    Instance instance = createInstance(text); // 构建待分类的实例
    double label = classifier.classifyInstance(instance); // 进行分类
    return train.classAttribute().value((int)label); // 返回分类结果
  }

  private Instance createInstance(String text) {
    Instance instance = new DenseInstance(1);
    instance.setValue(0, text);
    instance.setDataset(new Instances(createAttributes(), 1));
    return instance;
  }

  private Instances createAttributes() {
    FastVector attributes = new FastVector();
    attributes.addElement(new Attribute("text", (FastVector) null));
    attributes.addElement(new Attribute("class", createClasses()));
    Instances instances = new Instances("data", attributes, 0);
    instances.setClassIndex(1);
    return instances;
  }

  private FastVector createClasses() {
    FastVector classes = new FastVector();
    classes.addElement("positive");
    classes.addElement("negative");
    return classes;
  }

}

mvn package
java -jar target/myproject-1.0-SNAPSHOT.jar

curl --request POST 
  --url http://localhost:8080/predict 
  --header 'content-type: application/json' 
  --data '{"text": "这个电影真是太好看了！"}'