Исследование осознания своей социальной проактивности первокурсниками университета.pdf 1. Int roducti onThe importance of applied studies of pattern recognition techniques relieson the fact that all effort for technology development should target practicalresults for society. In this sense, largely scrutinized techniques are beingapplied to solve practical problems in many domains. This paper approachesthe problem related to the management of social groups in an educationcontext. In order to adequately deal with the convergent characteristics of agroup of students, it is necessary to enlighten some key characteristics. Thejuvenile leadership expresses a concept of adolescents as rights subject, withpower to democratically participate in social change [1]. Juvenile leadershipis a way to face violence and alienation among young people [2, 3]. Thus, it isnecessary to know the social willingness of the young in a process of educationfor values.A case study is reported, in which a self-perception survey of newundergraduate students for social proactivity is associated with socioeconomicfeatures. Data Mining over the students' data base was driven under theguidelines of CRISP-DM. The detected predominance of non-proactivityencourages new studies to assess possible links between this finding andexisting socio-cultural features.2. Problem st atementAccording to Maturana and Varela [4], an autopoietic machine has anetwork of processes of production of components which: (i) continuouslyregenerate the network of processes that produced them; and (ii) constitute themachine as a concrete unity in space in which the components exist. The worldis not finished and pre-given. Instead of seeing ourselves as fully conditionedbeings, we find that there is a space for action and building a better society.Experience is tied to our structure, so that one can not separate the individualhistory of biological and social actions in relation to the outside world. In thissense, humans are considered as autopoietic experiencing structural, natural,social, cultural, and linguistic relations. By doing this, the baseline to studyproactivity is set.The language makes possible the communication phenomenon with anexchange of meanings in a social and cultural network of interactions. Thisdynamics takes place inside the social context, in a mutual coupling of anetwork of reciprocal interactions, which are formed in the so-called thirdorderunits (social and cultural engagement). There are continuity and changeprocesses in socio-cultural orientations that are related to undergraduatestudy, in accordance with critical analysis of habitus Bourdieusian concept onthe social nature of human behavior [5]. Thus one can go beyond a purelyobjectivist perspective (living conditions, independent of human action) orsubjective perspective (human action without considering socio-culturalconditions where action occurs).Any subject is able both to organize themselves in response to disturbancesof physical and socio-cultural environment (reactivity), and also organize thisenvironment (proactive). So, he is structured and structuring.The language has a fundamental role in social interaction, producinga structural coupling, which carries images, showing different forms ofobservation and perception of reality by means of symbols (culture, interests,power, beliefs, values, illusions, blind spots). The problem that arises is theidentification of proactivity as the possibility of transforming society from theperspective of social inequality.This paper aims at identifying and analyzing the self-perception of the youngin relation to willingness for social proactivity. It describes the perception ofa group of new comers in undergraduate studies on the proactivity in socialtransformation, from the texts of essays and data from the socioeconomicquestionnaire, using a Data Mining technique.3. Mate rial and meth ods3.1 The data setThe training dataset was obtained from a socioeconomic questionnairealong with data extracted from essays from an entrance examination. It includesdata like schooling and work of the parents, the English knowledge level, thewriting grade, and the candidate occupation. Moreover, features that identifythe proactiveness were extracted from the candidate writings. For example,the use of the pronouns I or We when approaching the social inequality,depending on the text construction, may be interpreted as the willing of socialproactivity.3.2 The mining procesData Mining was driven under the CRISP-DM (Cross Industry StandardProcess for Data Mining) guidelines, the well-known method that proposes aset of tasks organized in phases, generic tasks, specialized tasks, and processinstances [6]. The core of the method is the model building that was carriedout by applying the Combinatorial Neural Model (CNM), a hybrid neuralnetwork that represents an alternative to overcome the black box limitation ofthe Multilayer Perceptron. This is achieved due to a particular characteristic ofthe model that is built up on a neural network structure along with a symbolicprocessing [7, 8].CNM can identify relations among input vectors and output values,performing a symbolic mapping. It uses supervised learning and a feedforwardtopology with three layers (Fig. 1):Fig. 1. Example of a combinatorial neural network(i) the input layer, in which each node corresponds to a triple objectattribute-value that describes a dimension (here called evidence and denotedby e) in the domain;(ii) an intermediary or combinatorial layer with neurons connected to oneor more neurons from the input layer, representing the logical conjunctionAND; and(iii) the output layer, with one neuron for each possible class (here calledhypothesis and denoted by h), that is connected to one or more neurons in thecombinatorial layer by the logical disjunction OR.The synapses may be inhibitory or excitatory and have assigned a weightbetween zero (unconnected) and one (fully connected). The network is createdas follows: (i) one neuron in the input layer for each evidence in the trainingset; (ii) a neuron in the output layer for each class in the training set; and(iii) one neuron in the combinatorial layer for each possible combination ofevidences (with order ≥ 2) from the input layer. Combinations of order = 1are connected directly to the output layer. CNM is trained according to thealgorithm in Fig. 2.For the sake of simplicity, without quality loss, we used a constant value1 for the evidential flow. For CNM training, examples are presented to theinput layer, triggering a signal from each neuron matching to the combinatoriallayer, having their weights increased. Otherwise, their weights are weakened.After training, the accumulators associated to each arc in the outputlayer will belong to the interval [-c, c], where c is the number of cases in thetraining set. After the training process, the network is pruned, based on theaccumulators values, as follows: (i) remove all arcs arriving to the output layerwith accumulators below a threshold specified by the user; and (ii) remove allneurons and arcs from the input and combinatorial layers disconnected afterthe first step.The relations that remained after pruning are rules that are considered inthe application domain.Two basic metrics are applied during the model generation that allowthe evaluation of the resulting rules: Confidence (C) and Support (S). CIFig. 2. Learning algorithm for CNM.(Confidence Index) express the degree of cohesion between the premises(the antecedent A) and the conclusion (the consequent C) and indicates thepercentage of cases that occurred (antecedent associated with the consequent),compared to the antecedent [9]. ThusCI =100*(A ∩ C) / AS indicates the percentage of occurrence of the rule, compared to theconsequent. SoS = 100*(A ∩ C) / CThe main problem with CNM is its low performance due to the exponentialgrowing of the combinatorial layer. However, it received many improvementsthat have turned it feasible as a useful approach for building classifiers [9, 10,11, 12, 13, 14, 15].3.3 CNM uti lizati on det ailsThe sample in the present study comprises 98 randomly selected studentsfrom entrance examination courses, representing 20% of the population.The input data set refers to the answers to the socio-economic questionnaire(objective responses) and to the essays texts that were later transformed intostructured data.Socio-economic questionnaire contains 30 attributes on personal data, pasteducation data, future education data, and family conditions data.The instrument of analysis of the essays was built by defining the type ofknowledge to be discovered in texts, according to Fig. 3.The phenomena of social inequality included the following possibilities:nationality, richness and poorness, housing, ethnicity, sex, gender, generations,rural and urban, center and periphery, qualification to work, schooling, culture,religion, social class, related to children, teen pregnancy, drugs, violence,murder, and other. Factors responsible for social inequality are: I, we, youngpeople, society in a general sense, civil society, politicians, government,religious authorities, elite, political parties, businessmen, non-governmentorganizations, financial systems, education, employers, employees, birth rates,poor people, bandits, human nature, and others. Processes or systems that causeFig. 3. Social Inequality and equalityCATEGORY SUBCATEGORYInequality contextPhenomenaResponsibleProcessesChanges AgentsProcessesEquality horizonCertaintyHopeDesperationor stimulate social inequality are: neoliberalism, capitalism, globalization,socialism, oppression, corruption, asymmetry of power, prejudice, moderatedpolitics, education, media, ideology factors, public policy, and others.Social change agents can be the same as factors that cause social inequality.Processes and dynamics of social change include fight, radicalization, history,proactivity, public policy, education, law, science, competition, ethicalpoliticalinstances, values, religion, ecology, election, and other.The target variable or attribute classifier was proactivity, understoodoperationally as expressions contained in the texts of essays concerningsocial change, which had as action subject or action intention the I or we.Thus, this attribute has four possibilities as domain description: (i) pro-activeyoung, (ii) non pro-active young, (iii) pro-active adult or (iv) non pro-activeadult. Attribute proactivity were derived from attribute I or we, along withattribute age. Entrance examination participants were considered young if s/he was under 25 and adult otherwise. The data obtained were included into thedatabase of socio-economic questionnaire. Attributes with frequency under 10and over 96 were excluded, as well low discriminative skill.4. Res ultsThe essays were anonymously analyzed by three teachers with master degreein Arts and experience in correcting essays, based on the previously describedinstrument (Fig. 3). The Pearson correlation between the classifications obtainedby the three professors who evaluated the essays was 0.75 between teachers Aand B, 0.80 between teachers A and C, and 0.85 between the teachers B andC. Therefore, we obtained a positive correlation, above moderate and belowstrong, according to Levin [16]. The final value assumed for the target variablewas defined on the basis of a majority criteria, i.e., when at least two readersagreed with the value.On average, the number of attributes found by essay was 7 among 96 attributes,and 5.3 among the attributes potentially significant, i.e., with a minimum 10%support. The categories with support less than 10% were excluded from thetraining base. Regarding the 96 attributes of the instrument of initial analysisof essays, 19 of them were potentially significant, representing a recovery ofabout 20%. The database for mining has 52 attributes, 33 of the socio-economicquestionnaire and 19 of the instrument of essay analysis. The scores achievedby entrance examination participants in sample ranged from 0-17 on a 0-20points scale. The average was 9.12 and the standard deviation was 3.34.It was selected 71 rules from a total of 1640 generated. The selected ruleswere those that reached a CI value not less than 90% and a level of supporthigher than 10%. Fig. 4 shows some of such rules.Premise Conclusion CI Cases SThe applicant has provided only aentrance examination ANDThe father has regular work ANDYour writing grade ∈ [mean, mean +standard deviation]Non ProactiveYoung 100.00 % 7 14.29 %The father's schooling is to completehigh school ANDThe mother works regularly ANDThe protagonist of social change isthe GovernmentNon ProactiveYoung 100.00% 7 14.29 %The candidate is not a paid job ANDTheir level of understanding ofEnglish is regular ANDYour note writing ∈ [mean, mean +standard deviation]Non ProactiveYoung 100.00% 7 14.29 %5. Dis cussi onThe predominant profile in the sample is the non pro-active young, towhom social change depends upon the actions of other social agents, ratherthan from them. All the standards listed below that describe this non proactiveyoung, come from the selected rules (those with CI ≥ 90% and S > 10%).The non pro-active young people assign the responsibility for proactiveness insocial change to the government and to the non profession oriented courses heattended in private schools.He concluded high school less than three years ago, he has alreadyparticipated in an entrance examination, he has a regular understanding ofEnglish, he belong to families with up to five dependents in family income, hisfather has undergraduate studies and works regularly, and his mother has highschool studies and works regularly.For non proactive adults, the CNM describes combinations of the followingfeatures: 100% CI and 26.92% support:- humanities as entrance examination area;- enrolled in the Social Services, and- finished high school for over three years. 80% CI and 44.44% support:- married,- the mother is retired, and- the father is educated only up to 4th grade of elementary school. 80% CI and 15.38% support:- attended a profession oriented high school;- high school studies in public school;- finished high school for over three years;- attended an entrance examination course for one year;- married;- monthly family income is 1-3 times the minimum wage;- his father is retired or died without leaving a pension;- his mother has finished elementary school, while his father completed theprimary school;- follows another religion (other than those mentioned in thequestionnaire);- already participated in two entrance examinations;- points out difference between social classes as a phenomenon of socialinequality;- to reduce social inequality, suggests paths to education and publicpolicy.Young students that were classified as proactive have an employed motherin a small business. Here, CI is less than 90% (75% CI and 21.43% support).As the candidates were classified as not the most pro-active, the rules generatedby CNM revealed patterns just for that category.The most highlighted social agent was government. The most prominentmechanisms toward social changes were public policies, especially educationand employment.6. Conclusi onIt was possible to detect two distinct profiles of entrance examinationparticipants: the non proactive young and the non proactive adult, sincenon proactivity was the main feature in the studied group. The generatedmodels effectively subsidize the decision making in the other dimensions ofschool management, such as: administrative, financial, publicity, advertising,communication, and marketing. Achieved results reflect the perceptions ofyoung people, according to their social, historical, and cultural conditions, as astarting point for a joint educational effort.Some issues need to be further investigated:(i) The relationship between age, religious belief, education for humanvalues and proactivity in social change;(ii) The adoption of a taxonomy for the social proactivity, beyond thesimple dualism proactive/non proactive;(iii) The inclusion of other characteristics (being a lazy or an affirmativeperson, for example) based on the handwriting style can be fruitful to enrichthe understanding of individual classes.Results show that current approach is useful for educational institutions aswell as for any other domain where one can subjectively gather data concerningpersonal opinions.

Скачать электронную версию публикации