Target-Aspect-Sentiment Joint Detection with CNN Auxiliary Loss for Aspect-Based Sentiment Analysis (CNN 보조 손실을 이용한 차원 기반 감성 분석)
-
- Journal of Intelligence and Information Systems
- /
- v.27 no.4
- /
- pp.1-22
- /
- 2021
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.
This study is based on the research of the first year, which is the National Research Foundation of Korea's R&D subject for middle-grade researchers. In this study, the practical curriculum development of the education for love - an according to the psychoanalytic perspectives of F. Dolto(1908-1988) - is suggested as follows. The first is 'the reconstruction of the directions of curriculum and its specific aims in accordance with such directions.' The reconstruction of the directions of curriculum aims at leading our future generation to live as a subject of desire through the mutual-communication of love. The second is 'the reconstruction of the tasks of curriculum and its specific contents in accordance with such tasks.' The reconstruction of the tasks of curriculum pursuit to help our future generation through the converting the education for love into the paradigm of desire of Agape to live as a subject of desire forming a whole personality and practicing the desire of Agape in daily life. as a source of desire. According to these aims, the reconstruction of directions of curriculum are presented as following: firstly, 'curriculum for the mutual-communication between subjects of love' and secondly, 'curriculum for the subject of desire'. The reconstruction of tasks of curriculum are like these: firstly, 'converting the education for love into the paradigm of desire of Agape', and secondly, 'forming a whole personality through the education for love'. Thus, with respect to two specific aims in accordance with the reconstruction of directions are suggested like these: Firstly, 'constructing a subject as a speaking existence' and secondly, 'realizing the subject as the autonomous source of desire'. In the two specific contents in accordance with the reconstruction of tasks are presented as following: Firstly, 'realizing the truth of the desire of Agape'.' Secondly, 'practicing the desire of Agape in daily life.' The third is 'the reconstruction of curriculum by life cycle' are suggested. They include the fetal life, infants and preschool children life, and childhood life. In further study, it is required to contain adolescent period. It will be useful to help them to recover their self-esteem with the experience of true love, especially, out-of-school young generation overcome negative perspectives and prejudice in the society, and challenges to their dreams and future through proper utilization of the study outcome. The outcome of this study, which presented practical curriculum development of the education for love based on the understanding of psychoanalytic 'desire of subject' can be used as basic teaching materials for our future generations. Furthermore, the results can be used as a resource for educating ministers and lay leaders in the religious world to build capabilities to heal their inner side as well as the society that is tainted with various forms of conflict. These include general conflicts, anger, pleasure and addiction, depression and suicide, violence and murder, etc. The study outcome can contribute to the prevention of antisocial incidents against humanity that have recently been occurring in our free-semester system implemented in all middle schools across the country to be operated effectively. For example, it is possible to provide the study results as lecture and teaching materials for 'character camp' (self-examination and self-esteem improvement training) and 'family healing camp' (solution of a communication gap between family members and love communication training), which help students participate in field trip activities and career exploration activities voluntarily, independently, and creatively. Ultimately, it can visibly present the convergent research performance by providing the study outcome as preliminary data for the development of lecture videos and materials including infant care and preschool education, parental education, family consultation education, and holistic healing education. Support from the religious world, including the central government and local governments, are urgently required in order for such educational possibilities to be fulfilled both in the society and the fields of church education and to be actively linked to follow-up studies.
From January 2020 to October 2021, more than 500,000 academic studies related to COVID-19 (Coronavirus-2, a fatal respiratory syndrome) have been published. The rapid increase in the number of papers related to COVID-19 is putting time and technical constraints on healthcare professionals and policy makers to quickly find important research. Therefore, in this study, we propose a method of extracting useful information from text data of extensive literature using LDA and Word2vec algorithm. Papers related to keywords to be searched were extracted from papers related to COVID-19, and detailed topics were identified. The data used the CORD-19 data set on Kaggle, a free academic resource prepared by major research groups and the White House to respond to the COVID-19 pandemic, updated weekly. The research methods are divided into two main categories. First, 41,062 articles were collected through data filtering and pre-processing of the abstracts of 47,110 academic papers including full text. For this purpose, the number of publications related to COVID-19 by year was analyzed through exploratory data analysis using a Python program, and the top 10 journals under active research were identified. LDA and Word2vec algorithm were used to derive research topics related to COVID-19, and after analyzing related words, similarity was measured. Second, papers containing 'vaccine' and 'treatment' were extracted from among the topics derived from all papers, and a total of 4,555 papers related to 'vaccine' and 5,971 papers related to 'treatment' were extracted. did For each collected paper, detailed topics were analyzed using LDA and Word2vec algorithms, and a clustering method through PCA dimension reduction was applied to visualize groups of papers with similar themes using the t-SNE algorithm. A noteworthy point from the results of this study is that the topics that were not derived from the topics derived for all papers being researched in relation to COVID-19 (