• Title/Summary/Keyword: unbalance

Search Result 1,202, Processing Time 0.02 seconds

Subject-Balanced Intelligent Text Summarization Scheme (주제 균형 지능형 텍스트 요약 기법)

  • Yun, Yeoil;Ko, Eunjung;Kim, Namgyu
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.2
    • /
    • pp.141-166
    • /
    • 2019
  • Recently, channels like social media and SNS create enormous amount of data. In all kinds of data, portions of unstructured data which represented as text data has increased geometrically. But there are some difficulties to check all text data, so it is important to access those data rapidly and grasp key points of text. Due to needs of efficient understanding, many studies about text summarization for handling and using tremendous amounts of text data have been proposed. Especially, a lot of summarization methods using machine learning and artificial intelligence algorithms have been proposed lately to generate summary objectively and effectively which called "automatic summarization". However almost text summarization methods proposed up to date construct summary focused on frequency of contents in original documents. Those summaries have a limitation for contain small-weight subjects that mentioned less in original text. If summaries include contents with only major subject, bias occurs and it causes loss of information so that it is hard to ascertain every subject documents have. To avoid those bias, it is possible to summarize in point of balance between topics document have so all subject in document can be ascertained, but still unbalance of distribution between those subjects remains. To retain balance of subjects in summary, it is necessary to consider proportion of every subject documents originally have and also allocate the portion of subjects equally so that even sentences of minor subjects can be included in summary sufficiently. In this study, we propose "subject-balanced" text summarization method that procure balance between all subjects and minimize omission of low-frequency subjects. For subject-balanced summary, we use two concept of summary evaluation metrics "completeness" and "succinctness". Completeness is the feature that summary should include contents of original documents fully and succinctness means summary has minimum duplication with contents in itself. Proposed method has 3-phases for summarization. First phase is constructing subject term dictionaries. Topic modeling is used for calculating topic-term weight which indicates degrees that each terms are related to each topic. From derived weight, it is possible to figure out highly related terms for every topic and subjects of documents can be found from various topic composed similar meaning terms. And then, few terms are selected which represent subject well. In this method, it is called "seed terms". However, those terms are too small to explain each subject enough, so sufficient similar terms with seed terms are needed for well-constructed subject dictionary. Word2Vec is used for word expansion, finds similar terms with seed terms. Word vectors are created after Word2Vec modeling, and from those vectors, similarity between all terms can be derived by using cosine-similarity. Higher cosine similarity between two terms calculated, higher relationship between two terms defined. So terms that have high similarity values with seed terms for each subjects are selected and filtering those expanded terms subject dictionary is finally constructed. Next phase is allocating subjects to every sentences which original documents have. To grasp contents of all sentences first, frequency analysis is conducted with specific terms that subject dictionaries compose. TF-IDF weight of each subjects are calculated after frequency analysis, and it is possible to figure out how much sentences are explaining about each subjects. However, TF-IDF weight has limitation that the weight can be increased infinitely, so by normalizing TF-IDF weights for every subject sentences have, all values are changed to 0 to 1 values. Then allocating subject for every sentences with maximum TF-IDF weight between all subjects, sentence group are constructed for each subjects finally. Last phase is summary generation parts. Sen2Vec is used to figure out similarity between subject-sentences, and similarity matrix can be formed. By repetitive sentences selecting, it is possible to generate summary that include contents of original documents fully and minimize duplication in summary itself. For evaluation of proposed method, 50,000 reviews of TripAdvisor are used for constructing subject dictionaries and 23,087 reviews are used for generating summary. Also comparison between proposed method summary and frequency-based summary is performed and as a result, it is verified that summary from proposed method can retain balance of all subject more which documents originally have.

A study on the Awareness and Behavior about Sex of Middle School Students -from middle school students in Taegu area- (일부(一部) 중학생(中學生)의 성(性)에 대한 의식행태조사(意識行態調査))

  • Kim, Sang Ock;Nam, Chul Hyun
    • Journal of the Korean Society of School Health
    • /
    • v.5 no.2
    • /
    • pp.42-65
    • /
    • 1992
  • A survey was made of 976 students who were selected among students of 5 middle schools at Taegu so that it could furnish basic knowledge about sex education of adolescents by analyzing students recognition of sex, acquaintance with the opposite-sex, sex-education, The survery took a month from Nov. 1, to Nov 30, 1991. The results of this study are summarized as follows. 1. The general characteristics of the surveyed students. The survey consisted of 332 boys middle school student & 325 girls middle school students, 157 male & 162 female students of coeducational middle schools. 32.9% of them were from the first grade, 33.2% from the second grade & 33.9% from the third grade. 35.7% of them believed in Buddhism, 19% Christianism and the mode of their living standard, 86.7%, fell on 34.7% of their parents engaged in commerce and they were followed by salary man and public officals, 93.1 % of the students, parents were alive. 44.9% of their fathers were graduates of high school and 42.2% of their mothers middle school. 2. Sexual maturity 89.1 % of the surveyed girls had experienced menstruation. The mode of first menstruation, 48.2%, was at the age of 13 and the mean of it was 12.9, 3.7% the surveyed boys had exprienced a wet drem before. The mode of the first wet dream, 40.0%, was at the age of 14 and the mean was 13.4. 21.3% of surveyed students had the experience of masturbation but the number of girls fell far short of that boys. The mode of the first masturbation, 37.0%, was at the age of 14 and the mean was 13.4. 3. The acquaintance and sexual relations with the opposite sex 1) Analyzing the students actual conditions with the opposite, I found out that 52.3% of them wanted to have any kind of relations with the opposite and that 30.25 had already had some kind of relations. 73.2% of the students having relations with the opposite thought the other sex merely as a friend and the number of students who were thinking that way was distributed evenly among schools. 28.8% of the students had got acquainted with the other sex through their frieds and there were not much difference between boys and girls in the method of getting acquainated with the opposite. About 35.2% of the students having relations with the opposite came from the third grade. 47.8% of them answered that the meeting place was not fixed and 26.4% answered that they were meeting their parthers outdoors. 60.7% replyed that they were not disturbed in their studies by the relations with the other sex. 2) Most of the students 79.4%, answered that they had never had sexual relations and 16.3% of the rest said that thery were expressing their feelings by grasping each other's hand. 3) 16.6% of the surveyed students asid that they had the exprience of smoking, 1.1 % of an illusion caused by inhaling chemical addhesives, 44.0% of drinking and 41.4% of warching pornographic films. 4. The knowledge and attitude about the sex 1) The distribution and analysis according to schools and grades : 64.8% of the surveyed students answered correctly to the questions about mensturation, 49.3 % did so about wet dreams, 94.3 % did so about conception, 60.6% did so about child birth, 73.9% did so about AIDS and 50.1 % did so about sexual diseases. Roughly speaking, they had not much knowledge of sexual diseases. 2) The recognition of sex according to schools and grades : 39.0% of the students said that they had worries about sex. 33.1 % of what they worried was concerned with their bodies and 26.8% was about the acqaintance and relationship with the opposite sex. The girls were much more concerned about the former and the boys the latter. 51.1 % of the students asid that they had no specific opinion of masturbation but 19.2% said that's alright if self-restrained. About the sexual intercourse before marriage, 75.7% said negatively. 5. The need for sex education most of the students, 99.4% said they needed sex education and there was not much difference in that thought among schools. And 49.7% answered that schools, families, and societies were equlally important in sex education. About half of the students, exactly 50.2%. considered it as the main reason of sex education to prevent accidents cauesd by ignorance of sex. 81.4% said that they had had some kind of sex education. Most of the educations, 87.0%, had taken place at schools but 5.2% said they were getting most of the knowledge about sex from therir friednds, juniors and seniors. 59.5% of the students who had ever had a sex education said "Just so, so" when asked of the level of their contentment but the number of students who said "satisfied" was only a few, 16.1 %. 20.7% of the survered answered that thery wanted sex education to be made in the course of home life, and 26.6 % of the students most wanted to know about the acquaintance and relationship with the oppostie sex, 29.0% preferred nurse teachers as proper councellors of sex education. The mode of their present councellors, 42.0%, was friends but only 7.6% answered they dicussed with teachers. 6. The correlation analysis between general characteristcs and sexual behaviors of the surveyed students revealed that sex had a signigicant(P<0.001) positive correlation with parents' love toward students(P<0.01), the experience of masturbation, smoking, an illusion caused by inhaling chemical adhesives and the experience of watching pornographic films. And the standard of living had a significant(P<0.01) positive correlation(P<0.01) with grade point average, parents' existence(P<0.01) and parents' love, but a significant(P<0.01) negative correlation with sexual worries. grade point average had a significant(P<0.01)negative correlation with the experience of an illusion caused by chemical adhesives(P<0.01) and smoking. Parents' existence had significant(P<0.01) positive correlations with parents' love and smoking but a significant(P<0.01) negative correlation with the experience of an illusion by chemical adhesives. There was a significant(P<0.01) negative correlations between parents' love and the experience of an illusion by chemical adhesives, and a significant(P<0.001) positive correlation among masturbation and sexual worries, smoking, an illusion by chemical adhesives and the experience of watching pornographic films. There was a significant(P<0.001) positive correlation among acquaintance with the opposite sex, smoking, the experience of an illusion by chemical adhesives and watching pornographic films. Sexual worries had significant(P<0.01) positive correlations with smoking, the experience of an illusion by chemical adhesives and watching pornographic films. smoking had a significant positive correlation with drinking the experirence of, an illusion by chemical adhesives and watching pornographic films. Finally, there was a significant(P<0.01) positive correlation between the drinking experience and the illusion experience by chemical adhesives. According to the results mentioned above, the fact is certain that there is a great need for sex education of adolescents. Therefore, it is desirable that the schools teach sexual physiology and normal positively and that sex education including hygien education be an independant course in the curriculums. Furthermore, it is essential that the schools should have enough nurse teachers to take up sex education, expand training opportunities for them and that they develop educational materials. Considering the unbalance of the level of sex educations between boys and girls, I want to suggest that all boys and girls have sex education evenly and lead happy lives by correction irrational thought about sex, that is to say, sex discrimination, Sex education programs, especially of middle school students, should be reexamined if it is to give the students effective and profitable knowledge about sex. In addition, the government should establish a policy of adolescents' sex education to have healthy opinions of sex settled nationwide.

  • PDF