• Smart Media Journal
• /
• v.13 no.6
• /
• pp.35-43
• /
• 2024

During the post-pandemic period, the interest in foreign language learning surged, leading to increased usage of language-learning apps. With the rising demand for these apps, analyzing app reviews becomes essential, as they provide valuable insights into user experiences and suggestions for improvement. This research focuses on extracting insights into users' opinions, sentiments, and overall satisfaction from reviews of HelloTalk, one of the most renowned language-learning apps. We employed topic modeling and emotion analysis approaches to analyze reviews collected from the Google Play Store. Several experiments were conducted to evaluate the performance of sentiment classification models with different settings. In addition, we identified dominant emotions and topics within the app reviews using feature importance analysis. The experimental results show that the Random Forest model with topics and emotions outperforms other approaches in accuracy, recall, and F1 score. The findings reveal that topics emphasizing language learning and community interactions, as well as the use of language learning tools and the learning experience, are prominent. Moreover, the emotions of 'admiration' and 'annoyance' emerge as significant factors across all models. This research highlights that incorporating emotion scores into the model and utilizing a broader range of emotion labels enhances model performance.

• Asia pacific journal of information systems
• /
• v.34 no.2
• /
• pp.400-420
• /
• 2024

Nowadays, social media has evolved into a powerful networked ecosystem in which governments and citizens publicly debate economic and political issues. This holds true for the pros and cons of Indonesia's ore nickel export restriction to Europe, which we aim to investigate further in this paper. Using Twitter as a dependable channel for conducting sentiment analysis, we have gathered 7070 tweets data for further processing using two sentiment analysis approaches, namely Support Vector Machine (SVM) and Long Short Term Memory (LSTM). Model construction stage has shown that Bidirectional LSTM performed better than LSTM and SVM kernels, with accuracy of 91%. The LSTM comes second and The SVM Radial Basis Function comes third in terms of best model, with 88% and 83% accuracies, respectively. In terms of sentiments, most Indonesians believe that the nickel ore provision will have a positive impact on the mining industry in Indonesia. However, a small number of Indonesian citizens contradict this policy due to fears of a trade dispute that could potentially harm Indonesia's bilateral relations with the EU. Hence, this study contributes to the advancement of measuring public opinions through big data tools by identifying Bidirectional LSTM as the optimal model for the dataset.

• Science of Emotion and Sensibility
• /
• v.18 no.1
• /
• pp.103-110
• /
• 2015

Sentiment lexicon is an essential element for expressing sentiment on a text or recognizing sentiment from a text. We propose a graph-based semi-supervised learning method to construct a sentiment dictionary as sentiment lexicon set. In particular, we focus on the construction of domain-specific sentiment dictionary. The proposed method makes up a graph according to lexicons and proximity among lexicons, and sentiments of some lexicons which already know their sentiment values are propagated throughout all of the lexicons on the graph. There are two typical types of the sentiment lexicon, sentiment words and sentiment phrase, and we construct a sentiment dictionary by creating each graph of them and infer sentiment of all sentiment lexicons. In order to verify our proposed method, we constructed a sentiment dictionary specific to the movie domain, and conducted sentiment classification experiments with it. As a result, it have been shown that the classification performance using the sentiment dictionary is better than the other using typical general-purpose sentiment dictionary.

• The Research Journal of the Costume Culture
• /
• v.20 no.5
• /
• pp.709-724
• /
• 2012

This study examined the characteristics of costumes worn at Halloween parties, a form of cultural entertainment commonly seen in the U.S. The Halloween party culture involves children and adolescents wearing costumes, decorating their bodies, and mimicking famous characters. Furthermore, the types and motifs of Halloween costumes have become a means of expressing individuality. This study conducted empirical research on how such motifs were reflected in modern Halloween party-wear in order to provide basic data regarding the development and design of Halloween costumes and the formation of the related entertainment culture. This study researched the shape of costumes and the type of traditional motif presented in these costumes, as well as analyzed the symbolic meaning of each motif. The research process was as follows. First, this study investigated the origin and evolution of Halloween by researching precedent studies, books, and internet data. Second, this study extracted the types of traditional Halloween motifs by analyzing the characteristics and symbols of Halloween costumes commonly presented in such materials. After collecting 547 Halloween-related images from U.S. and Korean Internet websites, this study sorted and analyzed images that could represent traditional Halloween motifs. According to the results, representative traditional Halloween motifs included black cats, white rabbits, tridents, scarecrows, skull and bones, ghosts, witches, vampires, bats, werewolves, and jack-o-lanterns(pumpkins, etc.). The sentiments for such traditional Halloween motifs changed according to era and race. The symbolic meaning would continuously change - from positive to negative and vice versa - to reflect various socio-cultural phenomena. The results of this study are expected to be used as basic data for developing Halloween costume designs and the related entertainment culture.

• Journal of Digital Convergence
• /
• v.16 no.8
• /
• pp.99-107
• /
• 2018

The purpose of the study compares the difference between the carriers' reported large consumption emotion of customers in regards to the appearance of the crew. The research method was conducted for 15 days from March 11 to 25, 2018, and the number of valid samples was 289 in total. The results of the study showed that customers differ in the influence of perceived consumption sentiment between full service carrier and low cost carrier on uniform of flight attendant. Consumer sentiments perceived by low cost carriers are comfortable, familiar, and lively, and these results have proven that they are distinguished from low cost carriers by being clean, sophisticated, and large. The results of this study are significant when the airline has changed the crew uniform at the right time and considered it to be a marketing tool that is important to the image change of the company.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.201-211
• /
• 2009

Korean middle-aged women, who are securing economic stability of their own along with the national economic growth, have had much concern in their outward appearance. Especially, middle-aged women's concern of appearance triggered by their various social/leisure activities and appreciation of aesthetic sense leads to the interest in their outward appearance, thus naturally stimulating their purchasing sentiments. This paper attempts to identify the level of middle-aged women's concern of appearance and analyze how this level of concern affects their behavior in purchasing cosmetic products. Our analytical findings include: 1. From the t-test and distributional analysis of points of each factor on the group, the high-interest type 1 (108 persons) and low-interest type 2 (91 person) in terms of 'concern of appearance' turned out to exist. 2. Five factors of cosmetics-purchasing behavior were derived that are fashion-leading type, compulsive buying type, brand-dependent type, pondering type, planned buying type and loyal-to-brand type. 3. Cosmetics-purchasing behavior varied according to the subjects' level of concern of appearance.

• Korean Journal of Human Ecology
• /
• v.19 no.1
• /
• pp.75-89
• /
• 2010

The purpose of the study is to integrate multi-cultural families with special needs and situations into family living and Korean social groups. Nowadays there has been an increase in the number of international marriages. According to these changes, there are a variety of social problems such as cultural conflicts, domestic violence, difficulty in communication, and bad relationships between family members because of misunderstandings. These social problems can be alleviated by a family integration education program for multi-cultural families. This program was developed in order to help immigrant women in their initial settlement and to provide them with information on mutual culture of family living. The contents of the program consist of how to live a harmonious, understanding and hopeful family life. The method of evaluation is to survey the immigrant women's self esteem and conduct an interview. The results of the evaluation are to promote a positive relationship between family members. Also the family agreed to promote favorable sentiments toward each other. The program also had meaningful consequences for the improvement of the immigrants' realistic expectation of marriage and conflict resolution skills. I am hopeful that more elaborate programs for multi-cultural families will be developed in order to maximize the effect with appropriate education and support systems.

• Journal of the Korean Society of Costume
• /
• v.56 no.7 s.107
• /
• pp.1-17
• /
• 2006

This study purposed to examine Korean people's white clothes custom historically and to explain the aesthetic consciousness latent in the custom. Korean people preferred white clothes, even up to foreigners called them White-clad folk. Not only as in old historical literatures, but also in Soo-suh, Shin-Dang-suh including Sam-Kuk-Ji in China, white clothes were a real symbol to Korean people, ranging chronically far back to the age of ancient tribal countries, Sam-Kuk Period through Koryo Dynasty and even to modern age near the end of Chosun Dynasty, wearing with pleasure regardless of age, sex or social position. Even King himself in Koryo Dynasty is said to have worn white clothes when he was out of official hours. During the Koryo and Chosun Dynasty, white clothes were sometimes prohibited for various reasons including conflicts with the theories of yin-yang and the five elements but such regulations were not effective. To Korean people, white clothes were ordinary people's everyday dress as well as noble people's plain suits, saints' uniforms with religious meanings, ceremonial costumes, funeral garments, etc. The various uses show that white clothes have been worn by many people. The unique custom that a People have worn white clothes consistently for such a long time may contain very deep symbolic meanings representing the people's sentiments and spirits. The present study understood that the meanings come from religious sacredness, magical wish for brightness, the pursuit of purity originating from the people's national traits, assimilation with nature and the will to attain whole ascetic personality. Aesthetic attitudes based on aesthetic values summed up as sacredness, brightness, purity, assimilation with nature, asceticism, etc. are the aesthetic consciousness pursued by Koreans through their white clothes. For Koreans, white color is the origin of their color sense coming from primitive religions such as worshipping the sun and the heaven. In this way, Korean people's preference for white clothes began with primitive religions, was mixed with various social, cultural and religious influences and finally was settled as their durable spirit, symbol and beauty.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.3
• /
• pp.274-279
• /
• 2015

The main goal of this research is to build a sentiment analysis system which automatically determines user opinions of the Stanford Sentiment Treebank in terms of three sentiments such as positive, negative, and neutral. Firstly, sentiment sentences are POS tagged and parsed to dependency structures. All nodes of the Treebank and their polarities are automatically extracted from the Treebank. We train two Support Vector Machines models. One is for a node level classification and the other is for a sentence level. We have tried various type of features such as word lexicons, POS tags, Sentiment lexicons, head-modifier relations, and sibling relations. Though we acquired 74.2% in accuracy on the test set for 3 class node level classification and 67.0% for 3 class sentence level classification, our experimental results for 2 class classification are comparable to those of the state of art system using the same corpus.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.37 no.7
• /
• pp.984-999
• /
• 2013

This research examines the interrelation of clothes, colors and sentiments based on clothes and colors that stimulate sentiment. This study provides data that is useful to color therapy by means of clothes as medium. The survey for this study targeted 200 Pusan National University students who analyzed the colors of association and clothes colors for nine positive vocabularies (passion, love, warmth, happiness, interest, softness, comfortable, freshness, and coolness) and six negative vocabularies (anger, fear, despair, nervous, gloomy, and loneliness). The data collection process used 120 standard colors as represented by Munsell's basic 10 colors (R, YR, Y, GY, G, BG, B, PB, P, RP) as chromatic colors classified into eleven tones of colors (V, S, B, P, VP, LGR, GR, L, DL, DP, DK) and achromatic colors divided into ten steps of brightness N1-N10. The results of the research are as follows. First, the warm class of colors were significant in the colors of association with positive sentiment and the cold class of colors were significant in the sentiment of refreshment and coolness. In addition, bright and clear colors (like V, S, VP, P) were associated with color tones. Second, the low bright achromatic colors were generally high for the colors of association with negative sentiment; in addition, the color of R, PB, P (as achromatic colors) were also significant. In addition, sober and dark tones (like GR, DL, DK, DP) were significant in color tones. Third, the interrelation between positive sentiment and clothes colors shows that colors of association were mainly used for upper garment colors. Similar colors against upper garments were used together for bottom garment achromatic colors and complementary colors; therefore, bottom garments play a subsidiary role in the concept of coordination with upper garments.