JP5604344B2 - Vocabulary explosion time detection device, method, and program - Google Patents

Description

  The present invention relates to a vocabulary explosion time detection device, method, and program, and more particularly, to a vocabulary explosion time detection device, method, and program for detecting whether or not an infant has reached a vocabulary explosion time.

  Although human language development can provide important scientific knowledge and suggestions for thinking about `` what is human beings '', there are many unsolved problems at present, so progress in measurement technology related to language development There is almost no commercial service development. In particular, there has been little progress in science and technology related to vocabulary acquisition, among basic abilities such as speech recognition, vocabulary acquisition, and grammar manipulation. However, technological development in this field is considered to be important in view of the need for education that moderately supports healthy development and the early detection and support of developmental disabilities including language development delays.

  One of the most distinctive and important phenomena in infant language development is the vocabulary explosion (or vocabulary spurt). This is a phenomenon that development psychologists have been paying attention to since the middle of the 20th century, and refers to a rapid change in vocabulary learning speed that occurs in the second half of the year. Basically, toddlers begin to utter their first words around their first birthday, but for a while they learn words at a very moderate rate. However, after the age of one and a half years, the words suddenly start to utter, so the dramatic change has been called “explosion” and “spurt”. The vocabulary explosion is so dramatic that many parents consciously notice it, so it is well known not only in the field of psychology but also in the childcare industry.

  Conventionally, in the field of developmental psychology, the phenomenon of vocabulary explosion has been confirmed in multiple languages using large-scale group data using a vocabulary checklist (questionnaire survey based on parents' answers). It has been found that when the average value of the population data is plotted for each age, it becomes a quadratic curve showing a gradual increase, and its inflection point appears around 18-20 months. From these collective data, we have regarded vocabulary explosion as a common phenomenon seen in many children.

  With regard to this vocabulary explosion, the following four main points have been hitherto related to when the vocabulary explosion occurs for each individual and how to detect and estimate the vocabulary explosion time (the time when the vocabulary explosion starts). A method has been proposed.

  The first is a visual method in which a graph is drawn without any particular calculation and is visually determined. The second is the 50-word achievement standard method that defines the time when 50 words are learned as the vocabulary explosion time. The third is a specific period achievement standard method in which a period when an achievement standard (for example, 30 words or more) is satisfied in a specific period (for example, three weeks) is set as a vocabulary explosion period. The fourth is a logistic regression approximation method in which the velocity component of vocabulary acquisition data along the time axis is approximated to a logistic regression equation, and the inflection point is the vocabulary explosion time (see Non-Patent Document 1).

Ganger, J., & Brent, M. R. (2004). Reexamining the vocabulary spurt. Developmental Psychology, Vol. 40, No. 4, 621-632.

  However, the first method can confirm the presence or absence of the phenomenon to some extent, but has a problem that it is not suitable for accurately determining the vocabulary explosion time.

  The second method is based on empirical data, but based on a very small sample of English-speaking middle classes, there is no guarantee that it will apply to various children in many cultural zones. There is a problem. Another problem is that no individual differences in vocabulary explosion are assumed.

  The third method can detect changes in vocabulary acquisition speed over a specific time range, but the unique and arbitrary achievement criteria setting takes into account the vocabulary acquisition speed between individuals. There is a problem that some individuals may misunderstand the vocabulary explosion time completely.

  The fourth method is to approximate the data for each individual, even if the vocabulary acquisition speed between individuals is different, but it can not handle the characteristics of infant vocabulary development accurately, There is a problem that the approximation accuracy of logistic regression is low and the existence of the vocabulary explosion itself cannot often be confirmed. In addition, since this method is a type of estimation method that retroactively analyzes data accumulated to some extent, it cannot be used when the vocabulary explosion time is detected in real time as the child develops. There is also.

  The present invention has been made in view of the above problems, and even when there is not a lot of data after the vocabulary explosion, it is possible to detect whether the timing of the vocabulary explosion is approaching in real time in consideration of individual differences. An object of the present invention is to provide a vocabulary explosion time detection device, method, and program.

  In order to achieve the above-mentioned object, the vocabulary explosion timing detection device of the present invention provides an age at which an infant begins to speak a new word, and a cumulative number of words that the infant has spoken before the date. Among a plurality of data indicating the relationship with the number, approximation means for approximating a transition of data excluding the predetermined number of data from the larger age, a straight line approximated by the approximation means and the predetermined number Determination means for determining whether or not the data indicating the vocabulary explosion time of the infant is included in the plurality of data based on a difference from the data and a predetermined threshold value. Yes.

  According to the vocabulary explosion time detection apparatus of the present invention, the approximation means is a relationship between the age when the infant began to speak a new word and the cumulative number of words the infant began speaking before that age. The transition of data obtained by removing a predetermined number of data from the larger age among the plurality of data indicating the above is approximated by a straight line. Whether or not the data indicating the vocabulary explosion timing of the infant is included in the plurality of data based on the difference between the straight line approximated by the approximating means and a predetermined number of data and a predetermined threshold value. Determine whether.

  In this way, data indicating the relationship between the age at which the infant began to speak a new word and the cumulative number of words by capturing the characteristics of the vocabulary development of the infant, a predetermined number of data from the older age In order to determine whether or not there is a vocabulary explosion based on the difference between the straight line and a predetermined number of data, detect whether or not the vocabulary explosion is approaching in real time, taking into account individual differences. be able to.

  In addition, the determination unit calculates the difference while adding one by one from the data with the smaller age of the predetermined number of data, and when the difference exceeds the threshold, the determination unit calculates the difference. The maximum age among the data used can be detected as the vocabulary explosion time of the infant.

  The vocabulary explosion time detection method according to the present invention is a vocabulary explosion time detection method in a vocabulary explosion time detection apparatus including an approximation means and a determination means, wherein the approximation means allows an infant to speak a new word. Of a plurality of data indicating the relationship between the age of the child and the cumulative number of words that the infant has spoken before the age, data obtained by removing a predetermined number of data from the larger age The determining means approximates the transition of the child with a predetermined threshold based on a difference between the straight line approximated by the approximating means and the predetermined number of data, and a predetermined threshold. This is a method for determining whether or not data indicating the vocabulary explosion time is included.

  The vocabulary explosion time detection program of the present invention is a program for causing a computer to function as each means constituting the vocabulary explosion time detection device.

  As described above, according to the vocabulary explosion timing detection apparatus, method, and program of the present invention, the age and cumulative number of words at which an infant begins to speak a new word by capturing the characteristics of the infant's vocabulary development. In order to determine the presence or absence of a vocabulary explosion based on the difference between the number of data and the predetermined number of data from the older age, by linear approximation, and taking into account individual differences The effect of being able to detect whether or not the time of the vocabulary explosion is approaching in real time can be obtained.

It is a block diagram which shows the functional structure of the vocabulary explosion time detection apparatus of this Embodiment. It is a figure which shows an example of an input screen. It is a figure which shows an example of an input data set. It is a figure for demonstrating the detection of a vocabulary explosion time. It is a figure which shows the example of an output of a detection result. It is a flowchart which shows the content of the vocabulary explosion time detection processing routine in the vocabulary explosion time detection apparatus of this Embodiment.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  As shown in FIG. 1, the vocabulary explosion timing detection apparatus 10 according to the present embodiment outputs an input unit 12 that receives input of various data, a calculation unit 14 that determines the presence or absence of a vocabulary explosion, and a detection result. And an output unit 16.

  The input unit 12 is realized by an input device such as a known keyboard, mouse, or storage device, and receives input data.

  Here, in order to determine the timing of the infant's vocabulary explosion, what kind of data is referred to first becomes a problem. If it is possible to record all of the infant's utterances with electronic media such as a digital video recorder, it can be said that the most accurate method is to analyze it, but the cost of data acquisition is enormous and the infant's ambiguous utterance data Since there is no engineering technology that automatically recognizes and analyzes at the word level, it is very difficult to realize. On the other hand, there is also a method in which a questionnaire is answered every predetermined period (for example, once every three months) to grasp a change in the number of words newly spoken by an infant. In this case, if the predetermined period is long, it is difficult to grasp in real time whether or not the vocabulary explosion time has come. In addition, if the predetermined period is short, the burden on the respondent of the questionnaire (the parent of the infant) increases. Therefore, in practice, it is desirable to have a method capable of acquiring data at fine time points while reducing the burden on the parent who records the data.

  Therefore, in the present embodiment, data acquisition using the web diary method is applied. In this method, when an infant learns a new word (speaks), a specific site on the web is accessed via a network from a mobile phone or a personal computer, and the word that the infant remembers is recorded along with the diary of the day. (Non-Patent Document 2 “Tetsuo Kobayashi, Masaaki Nagata (2009),“ Infant Language Development Research Using the Web: Trial of Large-Scale Longitudinal Data Collection ”, Proc. 15th Annual Conference of the Language Processing Society, pp. 534-537., Non-Patent Document 3, “Tetsuo Kobayashi, Masaaki Nagata (March 2010),“ Reliability Verification of Infant Vocabulary Development Data Collected on the Web ”, 16th Annual Conference of the Language Processing Society of Japan See the collection of papers, pages 403-406.). The effectiveness of this method is very good in that it has been scientifically verified.

  In addition, the advantage of data acquisition by this method is that it is relatively easy for parents to record, but the date of recording (the date when the infant learned a new word) and the date of birth of the infant From the difference, it is possible to calculate the age at which the infant learned a new word. By using the data acquired in this way, the vocabulary explosion time detection device 10 according to the present embodiment can detect whether or not the vocabulary explosion time is approaching, in units of days.

  For example, an input screen 50 as shown in FIG. 2 is provided in the input unit 12 as an input interface to input data. In the input screen 50 of FIG. 2, a date input area 52, a word input area 54, a date of birth display area 56, and a registration correction button 58 are provided.

  In the date input area 52, the date (word acquisition date) when the infant spoke a new word can be input by direct input or selection from a pull-down menu. Further, when the input screen 50 is opened, the date of the day may be input as an initial value. In the word input area 54, the utterance and meaning of a word newly learned by the infant can be input by direct input. The date of birth display area 56 displays the date of birth of the infant registered in advance. When the date of birth is not registered, or when the registered date of birth is to be corrected, by pressing the registration correction button 58, the date of birth input screen is displayed and the input of the date of birth is accepted.

  By accepting the data entered in this way, as shown in Fig. 3, when (eg: September 12, 2009), what word (eg: doggie) and what meaning (eg: dog) was spoken A data set composed of the date of birth, the date of word acquisition, the utterance, and the meaning is obtained. It should be noted that the data set stored in the storage device in advance may be acquired.

  The calculation unit 14 is a computer that includes a CPU (Central Processing Unit), a RAM (Random Access Memory), and a ROM (Read Only Memory) that stores a program for executing a vocabulary explosion time detection processing routine described later. It is configured. The calculation unit 14 can be functionally represented by a configuration including a word acquisition age calculation unit 20, a straight line approximation unit 22, and a change point detection unit 24. The change point detection unit 24 is an example of the determination unit of the present invention.

  The word acquisition age calculation unit 20 indicates the date of acquisition of each word from the difference between the word acquisition date and the date of birth in the data set input from the input unit 12. Calculate age. For example, if the word acquisition date is “September 12, 2009” and the date of birth is “September 12, 2008”, the age of acquisition = September 12, 2009-September 12, 2008 = 365 days old. The calculated acquisition ages of the words are arranged in ascending order, and an integer series of 1, 2, 3,... Is assigned in ascending order to calculate the cumulative number of words (the most remembered word). Thereby, the data set which consists of a set of acquisition age and the number of accumulation words is generated.

  In addition, it is good also as a format which acquires in the input part 12 the data set which consists of a set of acquisition age and the cumulative number of words directly. In this case, the configuration of the word acquisition age calculation unit 20 can be omitted in the calculation unit 14.

  The straight line approximation unit 22 approximates a data set composed of a combination of the acquired age and the cumulative number of words with one straight line. In prior verification using actual data, it is known that the vocabulary learning speed before the vocabulary explosion can be linearly approximated with an accuracy of 80% or more. Therefore, each data is plotted on a coordinate system in which the cumulative number of words is the y-axis and the acquired age is the x-axis, and a straight line that minimizes the norm of each plotted data point is obtained. At this time, k data points are excluded from those having a larger acquired age, and linear approximation is performed using the remaining data points.

The change point detection unit 24 uses the vocabulary when the difference between the straight line obtained by the straight line approximation unit 22 and the k data points excluded when the straight line approximation unit 22 obtains the approximate straight line exceeds a predetermined threshold. Determine that an explosion has occurred. Specifically, as shown in FIG. 4, it is assumed that the time series of the cumulative number of words is y _i , the acquired age is x _i (1 ≦ i ≦ I), and plots up to i = n + k are obtained. Using up to nth data points (white circles in the figure) among the plotted data points, straight line approximation is assumed by the following equation (1), and straight line parameters a and b are obtained.

  Here, the square norm is used as the norm. Next, a difference dist between the straight line and the excluded k data points (black circles in the figure) is calculated by the following equation (2).

In addition, the difference dist value obtained by accumulating all k pieces is not obtained at a time, but the difference dist when i = n + 1 is first compared with the threshold d, and the data point and the straight line when i is increased by 1 are compared. Repeating the process of comparing the threshold value d while sequentially adding the differences to the dist, and when the difference dist exceeds the threshold value d for the first time, it is determined that the timing of the vocabulary explosion has come, and information indicating that there is a vocabulary explosion, And x _i when the difference dist exceeds the threshold d for the first time is output as the start date of the vocabulary explosion. If the difference dist does not exceed the threshold value d even after accumulating all k data points, information indicating that there is no vocabulary explosion (the vocabulary explosion time has not yet been reached) is output.

  The output unit 16 is mounted with a display, a printer, a magnetic disk, or the like, and the calculation result of the calculation unit 14 is output. For example, the calculation result is output to an output interface as shown in FIG. If a vocabulary explosion is detected, the date and time may be displayed together. Further, the input unit 12 accepts input of a predetermined date and time, compares the date and time with the detected vocabulary start date, and if the input date and time is before the vocabulary start date, Information indicating that there is no vocabulary explosion may be displayed, and if it is the start date of the vocabulary explosion, information indicating that the vocabulary explosion has been reached at that date may be displayed. In the example of FIG. 5, the start date of the vocabulary explosion is displayed in age.

  Next, a vocabulary explosion time detection processing routine executed in the vocabulary explosion time detection apparatus 10 of the present embodiment will be described with reference to FIG.

  In step 100, a data set composed of date of birth, word acquisition date, utterance, and meaning is obtained. Here, it is assumed that n + k pieces of data have been acquired.

  Next, in step 102, the acquisition age of each word is calculated from the difference between the date of acquisition and the date of birth of the data set acquired in step 100 above. Then, the calculated acquisition ages of the words are arranged in ascending order, and an integer series of 1, 2, 3,... Is assigned from the smallest to calculate the cumulative number of words. As a result, a data set composed of a set of the acquired age and the cumulative number of words is generated.

  Next, in step 104, the data set consisting of the combination of the acquired age and the cumulative number of words generated in step 102 is plotted on a coordinate system with the cumulative number of words on the y-axis and the acquired age on the x-axis. A straight line (y = ax + b) having a minimum norm is obtained by using up to nth data points among the plotted data points.

  Next, in step 106, 1 is set to the variable j. Next, in step 108, the straight line obtained in step 104 and the data from (n + 1) th to (n + j) th in accordance with the above equation (1). The difference dist from the point is calculated.

Next, in step 110, it is determined whether or not the difference dist calculated in step 108 has exceeded a threshold value d. When difference dist> threshold d, the process proceeds to step 112, and the data point (x _{n + j} , y _{n + j} ) is detected as a change point. On the other hand, if difference dist ≦ threshold d, the process proceeds to step 114 to determine whether j = k. If j ≠ k, the process proceeds to step 116, j is incremented by 1, and the process returns to step 108. On the other hand, in the case of j = k, it indicates that the difference dist does not exceed the threshold value d even if all the k data points are integrated, so the process proceeds to step 118 and the detection result indicating no change point is obtained. Output as.

Next, in step 120, if a change point is detected in step 112, information indicating that the vocabulary explosion is about to be reached, and the start date of the vocabulary explosion obtained from the change point (x _{n + j} , y _{n + j} ) _{xn + j} is output. If no change point is detected in step 118, information indicating that there is no vocabulary explosion is output, and the process ends.

  Actually, an experiment was performed using the values of k = 5 and d = 1.0 by the method of the present embodiment. When we verified the actual data for 15 people with this method, we succeeded in detecting the vocabulary explosion date with about 53% of data. In other words, this result seems to mean scientifically that the vocabulary learning speed changes at one change point.

  As described above, according to the vocabulary explosion timing detection device of the present embodiment, the data set of the acquired age of words and the cumulative number of words is captured for those who have a large age based on the characteristics of infant vocabulary development. In order to determine the presence or absence of a vocabulary explosion by detecting a change point where the difference between the straight line and the predetermined number of data exceeds the threshold, the vocabulary is taken into consideration in real time in consideration of individual differences. It is possible to detect whether or not an explosion is about to occur.

  As described above, the effects of accurately and quickly detecting the vocabulary explosion of infants are as follows: (1) Implementation of education according to the developmental stage that changes before and after the vocabulary explosion; (2) According to the individual vocabulary learning speed and characteristics (3) Early detection of children with developmental disabilities such as delayed language development and development of support education programs. Moreover, if it is managed centrally on the web from the time of acquisition of vocabulary development data, more effective early childhood education and childcare support will be possible, and it will have a great effect on society and industry as an ICT technology that supports an aging society with fewer children. there is a possibility.

  The present invention is not limited to the above-described embodiment, and various modifications and applications are possible without departing from the gist of the present invention.

  The above-described vocabulary explosion time estimation apparatus has a computer system inside, but the “computer system” includes a homepage provision environment (or display environment) if a WWW system is used. Shall be.

  In the present specification, the embodiment has been described in which the program is installed in advance. However, the program can be provided by being stored in a computer-readable recording medium.

DESCRIPTION OF SYMBOLS 10 Vocabulary explosion time detection apparatus 12 Input part 14 Calculation part 16 Output part 20 Word acquisition age calculation part 22 Straight line approximation part 24 Change point detection part

Claims (5)

Of a plurality of data indicating the relationship between the age at which an infant started speaking a new word and the cumulative number of words that the infant started speaking before the age, the one with the larger age Approximating means for approximating a transition of data obtained by removing a predetermined number of data from a straight line,
Based on the difference between the straight line approximated by the approximating means and the predetermined number of data, and a predetermined threshold value, whether or not the data indicating the infant vocabulary explosion time is included in the plurality of data. Determination means for determining;
Vocabulary explosion time detection device including.   The determination means calculates the difference while adding one by one from the smaller data of the predetermined number of data, and is used for calculating the difference when the difference exceeds the threshold value. The lexical explosion timing detection device according to claim 1, wherein the maximum age in the data is detected as the lexical explosion timing of the infant. A vocabulary explosion time detection method in a vocabulary explosion time detection device including an approximation means and a determination means,
The approximating means includes, among a plurality of data indicating a relationship between an age at which an infant comes to speak a new word and a cumulative number of words at which the infant comes to speak before the age, Approximate the transition of data excluding a predetermined number of data from those with the largest age, with a straight line,
The determination means includes data indicating the vocabulary explosion timing of the infant in the plurality of data based on a difference between the straight line approximated by the approximation means and the predetermined number of data, and a predetermined threshold. A method to detect when a vocabulary explosion occurs.   The determination means calculates the difference while adding one by one from the smaller data of the predetermined number of data, and is used for calculating the difference when the difference exceeds the threshold value. 4. The vocabulary explosion timing detection method according to claim 3, wherein the maximum age in the data is detected as the vocabulary explosion timing of the infant.   A vocabulary explosion time detection program for causing a computer to function as each means constituting the vocabulary explosion time detection device according to claim 1.

Images