CNN 보조 손실을 이용한 차원 기반 감성 분석

Abstract

텍스트를 바탕으로 한 차원 기반 감성 분석(Aspect-Based Sentiment Analysis)은 다양한 산업에서 유용성을 주목을 받고 있다. 기존의 차원 기반 감성 분석에서는 타깃(Target) 혹은 차원(Aspect)만을 고려하여 감성을 분석하는 연구가 대다수였다. 그러나 동일한 타깃 혹은 차원이더라도 감성이 나뉘는 경우, 또는 타깃이 없지만 감성은 존재하는 경우 분석 결과가 정확하지 않다는 한계가 존재한다. 이러한 문제를 해결하기 위한 방법으로 차원과 타깃을 모두 고려한 감성 분석(Target-Aspect-Sentiment Detection, 이하 TASD) 모델이 제안되었다. 그럼에도 불구하고, TASD 기존 모델의 경우 구(Phrase) 간의 관계인 지역적인 문맥을 잘 포착하지 못하고 초기 학습 속도가 느리다는 문제가 있었다. 본 연구는 TASD 분야 내 기존 모델의 한계를 보완하여 분석 성능을 높이고자 하였다.

이러한 연구 목적을 달성하기 위해 기존 모델에 합성곱(Convolution Neural Network) 계층을 더하여 차원-감성 분류 시 보조 손실(Auxiliary loss)을 추가로 사용하였다. 즉, 학습 시에는 합성곱 계층을 통해 지역적인 문맥을 좀 더 잘 포착하도록 하였으며, 학습 후에는 기존 방식대로 차원-감성 분석을 하도록 모델을 설계하였다. 본 모델의 성능을 평가하기 위해 공개 데이터 집합인 SemEval-2015, SemEval-2016을 사용하였으며, 기존 모델 대비 F1 점수가 최대 55% 증가했다. 특히 기존 모델보다 배치(Batch), 에폭(Epoch)이 적을 때 효과적으로 학습한다는 것을 확인할 수 있었다. 본 연구에서 제시된 모델로 더욱 더 세밀한 차원 기반 감성 분석이 가능하다는 점에서, 기업에서 상품 개발 및 마케팅 전략 수립 등에 다양하게 활용할 수 있으며 소비자의 효율적인 구매 의사결정을 도와줄 수 있을 것으로 보인다.;Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.