• Journal of Nutrition and Health
• /
• v.43 no.2
• /
• pp.181-188
• /
• 2010

Consumer perception of processed food and restaurant food's nutrient labelling was surveyed. The subjects of this survey consisted of 1,507 parents, whose ages were 20-59 years old. The ratio of the respondents that have known nutrition labelling on processed foods was 89.8% and the ratio of whom have checked the nutrition labelling at their point of purchase was 72.3%. The nutrients which were considered important for nutrition labelling were fat (57.1%), calorie (56.3%) and sodium (49.0%). Also nutrient which were able to be recognized at a glance by the subjects were in the order of trans fat (62.1%), cholesterol (26.9%), calorie (23.9%) and sodium (21.0%). If restaurant menu's nutrient labelling be enacted, the answer rate that the menu's nutrition labelling may affect their menu choice is 90.6% of the respondents. Besides of the Fastfoods that are enforcement, restaurants of that customers want the menu to be labeled were 'pizza and chicken restaurants'. Nutrients that customers preferred to be labelled were calorie (62.0%), fat (60.3%) and sodium (50.9%).

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.1-25
• /
• 2020

Sentiment Analysis (SA) is a Natural Language Processing (NLP) task that analyzes the sentiments consumers or the public feel about an arbitrary object from written texts. Furthermore, Aspect-Based Sentiment Analysis (ABSA) is a fine-grained analysis of the sentiments towards each aspect of an object. Since having a more practical value in terms of business, ABSA is drawing attention from both academic and industrial organizations. When there is a review that says "The restaurant is expensive but the food is really fantastic", for example, the general SA evaluates the overall sentiment towards the 'restaurant' as 'positive', while ABSA identifies the restaurant's aspect 'price' as 'negative' and 'food' aspect as 'positive'. Thus, ABSA enables a more specific and effective marketing strategy. In order to perform ABSA, it is necessary to identify what are the aspect terms or aspect categories included in the text, and judge the sentiments towards them. Accordingly, there exist four main areas in ABSA; aspect term extraction, aspect category detection, Aspect Term Sentiment Classification (ATSC), and Aspect Category Sentiment Classification (ACSC). It is usually conducted by extracting aspect terms and then performing ATSC to analyze sentiments for the given aspect terms, or by extracting aspect categories and then performing ACSC to analyze sentiments for the given aspect category. Here, an aspect category is expressed in one or more aspect terms, or indirectly inferred by other words. In the preceding example sentence, 'price' and 'food' are both aspect categories, and the aspect category 'food' is expressed by the aspect term 'food' included in the review. If the review sentence includes 'pasta', 'steak', or 'grilled chicken special', these can all be aspect terms for the aspect category 'food'. As such, an aspect category referred to by one or more specific aspect terms is called an explicit aspect. On the other hand, the aspect category like 'price', which does not have any specific aspect terms but can be indirectly guessed with an emotional word 'expensive,' is called an implicit aspect. So far, the 'aspect category' has been used to avoid confusion about 'aspect term'. From now on, we will consider 'aspect category' and 'aspect' as the same concept and use the word 'aspect' more for convenience. And one thing to note is that ATSC analyzes the sentiment towards given aspect terms, so it deals only with explicit aspects, and ACSC treats not only explicit aspects but also implicit aspects. This study seeks to find answers to the following issues ignored in the previous studies when applying the BERT pre-trained language model to ACSC and derives superior ACSC models. First, is it more effective to reflect the output vector of tokens for aspect categories than to use only the final output vector of [CLS] token as a classification vector? Second, is there any performance difference between QA (Question Answering) and NLI (Natural Language Inference) types in the sentence-pair configuration of input data? Third, is there any performance difference according to the order of sentence including aspect category in the QA or NLI type sentence-pair configuration of input data? To achieve these research objectives, we implemented 12 ACSC models and conducted experiments on 4 English benchmark datasets. As a result, ACSC models that provide performance beyond the existing studies without expanding the training dataset were derived. In addition, it was found that it is more effective to reflect the output vector of the aspect category token than to use only the output vector for the [CLS] token as a classification vector. It was also found that QA type input generally provides better performance than NLI, and the order of the sentence with the aspect category in QA type is irrelevant with performance. There may be some differences depending on the characteristics of the dataset, but when using NLI type sentence-pair input, placing the sentence containing the aspect category second seems to provide better performance. The new methodology for designing the ACSC model used in this study could be similarly applied to other studies such as ATSC.

• Journal of Nutrition and Health
• /
• v.43 no.5
• /
• pp.524-532
• /
• 2010

The Na, component of salt, can increase the risk of high blood pressure and hypertension. Especially, children are exposed to an increased risk of high sodium intake, because they often consume Na-rich processed foods and commercially prepared foods in the street. However, the database for the sodium and chloride content for these children's favorite foods is insufficient. In this study, the Na and Cl contents in 89 children's favorite foods were analyzed by using Instrumental Neutron Activation Analysis (INAA) method. The analyzed food items were presented after being classified into 33 kinds of food groups. The Na contents in 100 g children's favorite foods ranged from 0.3 mg to 35.1mg in fruits, 28.9mg to 82.5mg in milks, 127.2 mg to 602.2 mg in breads, cakes, sandwiches, and rice cakes, 2.5 mg to 1169.9 mg in candies, cookies and ice creams, 226.9 mg to 693.7 mg in commercially prepared street foods, and 103.4 mg to 875.8 mg in fast foods of westernized restaurant. Among children's favorite food groups, 100 g fried chicken, hotdog, burgers, and donuts contained an average Na of 536 mg, 553 mg, 794 mg, and 562.2 mg, respectively, so they are classified as 'high Na foods'. In contrast, 100 g fruits and dairy products contained Na an average 4.9 mg and 43.4 mg, respectively, being classified as 'low Na foods'. One serving of ramen, mandu noodle, and burger pizza can supply over 667mg Na, which is one third of the KDRI targeted intake. Likewise, the Cl contents in children's favorite foods were diverse according to food groups. The Cl contents in the analyzed foods differed from the 1.5 times of Na content, which is assumed in general. This study showed that the Na and Cl contents in children's favorite foods are very diverse. Conclusively, a strategy to reduce Na contents in the fast foods such as noodles and westernized restaurant foods is necessary for children health.

• Korean journal of food and cookery science
• /
• v.32 no.4
• /
• pp.476-491
• /
• 2016

Purpose: This study investigated consumers' perception of food safety and risk from foodborne illness and consumption pattern of meat and processed meat products in Korea. Methods: A quantitative survey was performed by trained interviewers, surveying 1,500 adults who were randomly selected from six major provinces in Korea. Results: Most of the respondents reported foodborne illness risk related to the consumption of raw meat but not related to heated meat and processed meat products. As respondents perceived the risk of food poisoning from raw meat, the purchase and intake decreased (p<0.001). Most of the respondents considered a low possibility of foodborne illness at home. Seventy-seven percent of the respondents thought that bacteria and virus are the main causes of foodborne illness. Improper storage practice (40.7%) and unsafe food material (29.3%) were the main risk factors contributing to foodborne illness. Perception and practice of food safety was significantly different by the residency area. The most preferred meat, processed meat, and processed ground meat products were pork (58%), ham (31.1%), and pork cutlet (40.4%), respectively. The most preferred cooking method was roasting, regardless of the type of meat, but the second preference for cooking method was significantly affected by the type of meat (p<0.001): stir-fried pork, beef with seasoning, fried-chicken and boiled duck. Frequency of eating out was 0.75/day on weekdays and 0.78/day on weekends at the mainly Korean BBQ restaurant. Conclusion: The results of this study could be used to develop science-based education materials for consumer and the specific guideline of risk management of meat and processed meat products.

• Journal of Food Hygiene and Safety
• /
• v.38 no.5
• /
• pp.402-408
• /
• 2023

Consumer interest in food nutrition continues to grow; however, research on consumer preferences related to nutrition remains limited. In this study, big data analysis was conducted using keyword logs collected from the national information service, the Korean Food Composition Database (K-FCDB), to determine consumer preferences for foods of nutritional interest. The data collection period was set from January 2020 to December 2022, covering a total of 2,243,168 food name keywords searched by K-FCDB users. Food names were processed by merging them into representative food names. The search frequency of food names was analyzed for the entire period and by season using R. In the frequency analysis for the entire period, steamed rice, chicken, and egg were found to be the most frequently consumed foods by Koreans. Seasonal preference analysis revealed that in the spring and summer, foods without broth and cold dishes were consumed frequently, whereas in fall and winter, foods with broth and warm dishes were more popular. Additionally, foods sold by restaurants as seasonal items, such as Naengmyeon and Kongguksu, also exhibited seasonal variations in frequency. These results provide insights into consumer interest patterns in the nutritional information of commonly consumed foods and are expected to serve as fundamental data for formulating seasonal marketing strategies in the restaurant industry, given their indirect relevance to consumer trends.