Vertex AI는 예측을 요청한 후 모델의 목표에 따라 결과를 반환합니다. 감정 분석 모델의 예측은 문서의 전반적인 감정을 반환합니다. 감정은 0에서 모델의 최대 감정 점수까지의 정수로 표시됩니다. 이 점수는 10보다 작거나 같습니다. 모델의 최대 감정 값은 학습 중에 설정됩니다. 예를 들어 최대 감정 점수가 2인 데이터 세트로 모델을 학습시킨 경우 예측 감정 점수는 0(부정), 1(중립), 2(긍정)일 수 있습니다.
일괄 예측 출력 예시
다음 샘플은 단일 문서에 대한 예측 결과입니다. 모델의 최대 감정 점수가 8이므로 이 샘플의 예측 감정은 명백히 긍정적입니다.
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-09-04(UTC)"],[],[],null,["# Interpret prediction results from text sentiment analysis models\n\n| Starting on September 15, 2024, you can only customize classification, entity extraction, and sentiment analysis objectives by moving to Vertex AI Gemini prompts and tuning. Training or updating models for Vertex AI AutoML for Text classification, entity extraction, and sentiment analysis objectives will no longer be available. You can continue using existing Vertex AI AutoML Text models until June 15, 2025. For a comparison of AutoML text and Gemini, see [Gemini for AutoML text users](/vertex-ai/docs/start/automl-gemini-comparison). For more information about how Gemini offers enhanced user experience through improved prompting capabilities, see [Introduction to tuning](/vertex-ai/generative-ai/docs/models/tune-gemini-overview). To get started with tuning, see [Model tuning for Gemini text models](/vertex-ai/generative-ai/docs/models/tune_gemini/tune-gemini-learn)\n\nAfter requesting a prediction, Vertex AI returns results based on your\nmodel's objective. Predictions from sentiment analysis models return the overall\nsentiment for a document. The sentiment is represented by an integer from 0 to\nthe model's max sentiment score, which can be equal to or less than 10. The\nmaximum sentiment value for a model is set during training. For example, if a\nmodel was trained on a dataset with a maximum sentiment score of 2, predicted\nsentiment scores can be 0 (negative), 1 (neutral), or 2 (positive).\n\nExample batch prediction output\n-------------------------------\n\nThe following sample is the predicted result for a single document. Because the\nmodel's maximum sentiment score is 8, the predicted sentiment for this sample is\nclearly positive.\n\n\n| **Note**: The following JSON Lines example includes line breaks for\n| readability. In your JSON Lines files, line breaks are included only after each\n| each JSON object.\n\n\u003cbr /\u003e\n\n\n```\n{\n \"instance\": {\"content\": \"gs://bucket/text.txt\", \"mimeType\": \"text/plain\"},\n \"prediction\": {\"sentiment\": 8}\n}\n```"]]