KNU Korean Sentiment Lexicon: Bi-LSTM-based Method for Building a Korean Sentiment Lexicon (Bi-LSTM 기반의 한국어 감성사전 구축 방안)
-
- Journal of Intelligence and Information Systems
- /
- v.24 no.4
- /
- pp.219-240
- /
- 2018
Sentiment analysis, which is one of the text mining techniques, is a method for extracting subjective content embedded in text documents. Recently, the sentiment analysis methods have been widely used in many fields. As good examples, data-driven surveys are based on analyzing the subjectivity of text data posted by users and market researches are conducted by analyzing users' review posts to quantify users' reputation on a target product. The basic method of sentiment analysis is to use sentiment dictionary (or lexicon), a list of sentiment vocabularies with positive, neutral, or negative semantics. In general, the meaning of many sentiment words is likely to be different across domains. For example, a sentiment word, 'sad' indicates negative meaning in many fields but a movie. In order to perform accurate sentiment analysis, we need to build the sentiment dictionary for a given domain. However, such a method of building the sentiment lexicon is time-consuming and various sentiment vocabularies are not included without the use of general-purpose sentiment lexicon. In order to address this problem, several studies have been carried out to construct the sentiment lexicon suitable for a specific domain based on 'OPEN HANGUL' and 'SentiWordNet', which are general-purpose sentiment lexicons. However, OPEN HANGUL is no longer being serviced and SentiWordNet does not work well because of language difference in the process of converting Korean word into English word. There are restrictions on the use of such general-purpose sentiment lexicons as seed data for building the sentiment lexicon for a specific domain. In this article, we construct 'KNU Korean Sentiment Lexicon (KNU-KSL)', a new general-purpose Korean sentiment dictionary that is more advanced than existing general-purpose lexicons. The proposed dictionary, which is a list of domain-independent sentiment words such as 'thank you', 'worthy', and 'impressed', is built to quickly construct the sentiment dictionary for a target domain. Especially, it constructs sentiment vocabularies by analyzing the glosses contained in Standard Korean Language Dictionary (SKLD) by the following procedures: First, we propose a sentiment classification model based on Bidirectional Long Short-Term Memory (Bi-LSTM). Second, the proposed deep learning model automatically classifies each of glosses to either positive or negative meaning. Third, positive words and phrases are extracted from the glosses classified as positive meaning, while negative words and phrases are extracted from the glosses classified as negative meaning. Our experimental results show that the average accuracy of the proposed sentiment classification model is up to 89.45%. In addition, the sentiment dictionary is more extended using various external sources including SentiWordNet, SenticNet, Emotional Verbs, and Sentiment Lexicon 0603. Furthermore, we add sentiment information about frequently used coined words and emoticons that are used mainly on the Web. The KNU-KSL contains a total of 14,843 sentiment vocabularies, each of which is one of 1-grams, 2-grams, phrases, and sentence patterns. Unlike existing sentiment dictionaries, it is composed of words that are not affected by particular domains. The recent trend on sentiment analysis is to use deep learning technique without sentiment dictionaries. The importance of developing sentiment dictionaries is declined gradually. However, one of recent studies shows that the words in the sentiment dictionary can be used as features of deep learning models, resulting in the sentiment analysis performed with higher accuracy (Teng, Z., 2016). This result indicates that the sentiment dictionary is used not only for sentiment analysis but also as features of deep learning models for improving accuracy. The proposed dictionary can be used as a basic data for constructing the sentiment lexicon of a particular domain and as features of deep learning models. It is also useful to automatically and quickly build large training sets for deep learning models.
As a result of the growth of Internet data and the rapid development of Internet technology, "big data" analysis has gained prominence as a major approach for evaluating and mining enormous data for various purposes. Especially, in recent years, people tend to share their experiences related to their leisure activities while also reviewing others' inputs concerning their activities. Therefore, by referring to others' leisure activity-related experiences, they are able to gather information that might guarantee them better leisure activities in the future. This phenomenon has appeared throughout many aspects of leisure activities such as movies, traveling, accommodation, and dining. Apart from blogs and social networking sites, many other websites provide a wealth of information related to leisure activities. Most of these websites provide information of each product in various formats depending on different purposes and perspectives. Generally, most of the websites provide the average ratings and detailed reviews of users who actually used products/services, and these ratings and reviews can actually support the decision of potential customers in purchasing the same products/services. However, the existing websites offering information on leisure activities only provide the rating and review based on one stage of a set of evaluation criteria. Therefore, to identify the main issue for each evaluation criterion as well as the characteristics of specific elements comprising each criterion, users have to read a large number of reviews. In particular, as most of the users search for the characteristics of the detailed elements for one or more specific evaluation criteria based on their priorities, they must spend a great deal of time and effort to obtain the desired information by reading more reviews and understanding the contents of such reviews. Although some websites break down the evaluation criteria and direct the user to input their reviews according to different levels of criteria, there exist excessive amounts of input sections that make the whole process inconvenient for the users. Further, problems may arise if a user does not follow the instructions for the input sections or fill in the wrong input sections. Finally, treating the evaluation criteria breakdown as a realistic alternative is difficult, because identifying all the detailed criteria for each evaluation criterion is a challenging task. For example, if a review about a certain hotel has been written, people tend to only write one-stage reviews for various components such as accessibility, rooms, services, or food. These might be the reviews for most frequently asked questions, such as distance between the nearest subway station or condition of the bathroom, but they still lack detailed information for these questions. In addition, in case a breakdown of the evaluation criteria was provided along with various input sections, the user might only fill in the evaluation criterion for accessibility or fill in the wrong information such as information regarding rooms in the evaluation criteria for accessibility. Thus, the reliability of the segmented review will be greatly reduced. In this study, we propose an approach to overcome the limitations of the existing leisure activity information websites, namely, (1) the reliability of reviews for each evaluation criteria and (2) the difficulty of identifying the detailed contents that make up the evaluation criteria. In our proposed methodology, we first identify the review content and construct the lexicon for each evaluation criterion by using the terms that are frequently used for each criterion. Next, the sentences in the review documents containing the terms in the constructed lexicon are decomposed into review units, which are then reconstructed by using the evaluation criteria. Finally, the issues of the constructed review units by evaluation criteria are derived and the summary results are provided. Apart from the derived issues, the review units are also provided. Therefore, this approach aims to help users save on time and effort, because they will only be reading the relevant information they need for each evaluation criterion rather than go through the entire text of review. Our proposed methodology is based on the topic modeling, which is being actively used in text analysis. The review is decomposed into sentence units rather than considering the whole review as a document unit. After being decomposed into individual review units, the review units are reorganized according to each evaluation criterion and then used in the subsequent analysis. This work largely differs from the existing topic modeling-based studies. In this paper, we collected 423 reviews from hotel information websites and decomposed these reviews into 4,860 review units. We then reorganized the review units according to six different evaluation criteria. By applying these review units in our methodology, the analysis results can be introduced, and the utility of proposed methodology can be demonstrated.
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.
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 (