A method and system for recommending low-forgetting English annotation styles based on AHP.

Abstract

This invention proposes a method and system for recommending English annotation methods with low forgetting rate based on the Analytic Hierarchy Process (AHP), belonging to the fields of optimization and intelligent decision theory. First, from the perspective of English learners, this invention analyzes and identifies five key factors affecting the rate of forgetting English vocabulary. Then, using the Analytic Hierarchy Process (AHP), a weight matrix that passes consistency detection is constructed for each influencing factor, and the actual influencing factor values ​​are normalized based on fuzzy logic. Based on the weight matrix that passes consistency detection and the normalized influencing factor scores under different text annotation methods, the estimated forgetting rate of English vocabulary for English learners under the corresponding annotation methods is obtained. The annotation method with the lowest estimated forgetting rate is selected as the optimal recommended annotation method to assist English learners in vocabulary learning. Finally, a one-month experimental verification of the proposed recommendation algorithm is conducted, and the experimental results demonstrate the effectiveness of this invention.

Description

Technical Field

[0001] This invention belongs to the fields of optimization and intelligent decision theory, and specifically relates to a method for recommending low-forgetting-rate English annotations based on the AHP method. Background Technology

[0002] English vocabulary plays a crucial role in English learning. The size of a student's vocabulary directly impacts their English listening, speaking, reading, and writing abilities, thus influencing their interest and enthusiasm for learning English. However, difficulty in memorizing vocabulary and easy forgetting are common problems and challenges faced by most students in the process of learning English vocabulary. According to the primacy effect proposed by American psychologist Luchins, the initial exposure to new words is crucial, and text annotation is one of the most frequently used and effective methods for students to initially memorize vocabulary. Text annotation is one of the most widely used vocabulary teaching methods in English teaching (Boersetal, 2017; Ko, 2012). Depending on the definition, text annotation can be divided into three types: native language annotation, English language annotation, and annotation in both native and English languages ​​simultaneously (Zhang & Ma, 2021).

[0003] Generally speaking, the choice of annotation method has a profound impact on the effectiveness of English vocabulary acquisition. Nagata (1999), in explaining the effectiveness of vocabulary acquisition, argued that the choice of annotation method is sometimes more effective than the use of a dictionary. This is because an optimized annotation method can quickly attract the attention of English learners. Furthermore, a suitable annotation method can also quickly enable English learners to connect semantics and achieve vocabulary acquisition through repeated exposure and deeper processing. Zhang Jing (2018) and Meng Chunguo, Chen Liping, and other scholars (2015) also found in their research that an optimized annotation method can, to some extent, promote incidental vocabulary acquisition by English learners.

[0004] On the other hand, English vocabulary memorization itself follows certain patterns. Exploring the impact of vocabulary forgetting patterns on English vocabulary learning can effectively assist in English vocabulary memorization. Generally speaking, vocabulary forgetting follows the well-known Ebbinghaus forgetting curve, meaning that immediately after memorizing vocabulary, the memory retention is 100%, after 20 minutes it is 58.2%, after 1 hour it is 44.2%, after 8-9 hours it is only 35.8%, and after a week it is only 25.4%. This shows that vocabulary forgetting decreases over time, exhibiting a trend of rapid initial forgetting followed by slower forgetting. Clearly, this forgetting pattern can be effectively applied to English vocabulary teaching. Specifically, in vocabulary teaching, learners can predict their forgetting rate based on the forgetting curve, set reasonable memorization time points, and conduct vocabulary consolidation and review to enhance memory, thereby converting short-term vocabulary memory into long-term memory. For example, Wang Ning (2021) pointed out the vocabulary memorization pattern based on the Ebbinghaus forgetting curve and applied it to students' vocabulary memorization training. His research shows that spaced repetition is more effective than rote memorization. Xie Jie (2020) studied the effect of the Ebbinghaus forgetting curve on high school students' English vocabulary memorization and found that this forgetting pattern can play a positive role in vocabulary memorization and even vocabulary use in daily life. In addition, some studies have suggested that the Ebbinghaus forgetting curve can more accurately interpret the brain's forgetting process, including forgetting time and forgetting speed (Jin Xinyue, 2019).

[0005] However, existing research rarely focuses on the relationship between text annotation style selection and vocabulary memorization. It fails to consider how students can reduce the forgetting trend of vocabulary when first learning it, and there are no relevant theories or methods for recommending low-forgetting English annotation styles. Furthermore, annotation style selection itself is a complex issue; the factors influencing the forgetting trend of English vocabulary involve multiple indicators and dimensions, and the degree of influence varies among different students. Summary of the Invention

[0006] To overcome the shortcomings of existing technologies, this invention proposes a method for recommending low-forgetfulness English annotation methods based on the AHP method, comprising the following steps:

[0007] Step 1: Identify the factors influencing the choice of English annotation methods;

[0008] Step 2: Construct a comparison matrix of influencing factors;

[0009] Step 3: Obtain the weight matrix of influencing factors and perform a consistency check on it. If it passes the check, save the weight matrix; otherwise, repeat steps 2 and 3 until the consistency check is passed.

[0010] Step four: For the incoming English learners, first assign influencing factor scores;

[0011] Step 5: Based on fuzzy logic theory, construct a normalization function for the influencing factors and normalize the scores of the above influencing factors.

[0012] Step 6: Based on the weight matrix that passed the consistency test and the normalized influencing factor scores under different text annotation methods, obtain the estimated value of English vocabulary forgetting rate of English learners under the corresponding annotation methods.

[0013] Step 7: Compare the estimated values ​​of English vocabulary memory forgetting under the different text annotation methods obtained above, and finally select the annotation method with the smallest estimated value as the best annotation method for the English learner.

[0014] Furthermore, the influencing factors in step one include: English proficiency (L), learning habits (H), learning ability (C), language environment (E), and mother tongue transfer (M).

[0015] Furthermore, the comparison matrix of influencing factors in step two is as follows:

[0016]

[0017] In the above formula, L, H, C, E, and M represent English proficiency, learning habits, learning ability, language environment, and mother tongue transfer, respectively. LL c LH c LC c LE c LM These represent the relative strength of English proficiency compared to English level, learning habits, learning ability, language environment, and mother tongue transfer in influencing vocabulary memorization when choosing a text annotation method. The interpretation principle for other symbols is the same.

[0018] Furthermore, based on the constructed comparison matrix of influencing factors, each column of the matrix is ​​processed as follows:

[0019]

[0020] Summing each row of matrix (2) and then obtaining its average value, we get the weight matrix W of each influencing factor as shown in the following formula:

[0021] W = (w L w H w C w E w M (3)

[0022] For convenience, each element in the influencing factor weight matrix W is denoted as w. i(i = L, H, C, E, M), where L represents English proficiency, H represents learning habits, C represents learning ability, E represents language environment, and M represents mother tongue transfer.

[0023] Furthermore, a consistency check is performed on each weight in the weight matrix. To do this, the following calculation is performed:

[0024]

[0025] Let each element in matrix W' be denoted as w. i '(i=L,H,C,E,M), w i 'with w i After performing the quotient operation, the largest eigenvalue of the weight matrix is ​​obtained as follows:

[0026]

[0027] Subsequently, the consistency index CI is calculated according to the following formula (6):

[0028]

[0029] In the above formula, n is the number of terms in the weight matrix;

[0030] Finally, the consistency detection index CR of equation (7) is obtained:

[0031]

[0032] Where RI is a constant.

[0033] Furthermore, the normalization calculation formula is as follows:

[0034] f:(x∈R)→(x U ∈[0,1]) (8)

[0035] In the formula, x represents the variable to be normalized, f(·) represents the normalization function, and x U Indicates the influencing factors after normalization;

[0036]

[0037] Where a, b, c, and d are constants; thus, we obtain the current English learner U. i The normalized measures of factors influencing vocabulary forgetting are as follows:

[0038]

[0039] In the formula, This represents the self-rating scores of each influencing factor obtained in step 5. and Representing learner Ui Normalized influencing factor values ​​for L, H, C, E, and M, where L represents English proficiency, H represents learning habits, C represents learning ability, E represents language environment, and M represents mother tongue transfer.

[0040] Furthermore, annotation methods include native language annotation, English annotation, and mixed native language and English annotation.

[0041] Furthermore, the estimated rate of forgetting of English vocabulary among English learners is obtained through the following process:

[0042] Learner U is obtained according to the following formula i Estimated English vocabulary forgetting rate when choosing annotation method mo

[0043]

[0044] In the formula, mo,mo∈{M',S',H'} represents annotation methods of native language annotation, English annotation, and mixed native language and English annotation, respectively.

[0045] Furthermore, the annotation method corresponding to the lowest estimated rate of forgetting of English vocabulary was selected as the best recommended annotation method. * ,Right now:

[0046]

[0047] This invention also provides a low-forgetting-rate English annotation recommendation system based on the AHP method, comprising:

[0048] The processor and memory are used to store program instructions, and the processor is used to call the stored instructions in the memory to execute a low-forgetting-rate English annotation recommendation method based on the AHP method as described in the above technical solution.

[0049] Compared with the prior art, the beneficial effects of the present invention are: the annotation method recommendation algorithm of the present invention can effectively reduce the rate of forgetting of students' vocabulary, thereby assisting English learners in vocabulary memorization. Attached Figure Description

[0050] Figure 1 This is a flowchart of the present invention.

[0051] Figure 2 This is a schematic diagram of the normalized function of factors affecting vocabulary forgetting. Detailed Implementation

[0052] The invention will now be further described with reference to the accompanying drawings.

[0053] To effectively predict the impact of different annotation methods on the forgetting trend of English vocabulary, this invention proposes a method for recommending low-forgetting English annotation methods based on the Analytic Hierarchy Process (AHP). The AHP method is a decision analysis method that combines qualitative and quantitative approaches, effectively unifying the handling of qualitative and quantitative factors in the decision-making process. For the low-forgetting English annotation method proposed in this patent, the advantage of using the AHP method is that it remains effective even when the learner's unique subjective judgment constitutes a major component of the factors influencing vocabulary forgetting. The flowchart of the proposed low-forgetting English annotation method based on the AHP method is shown below. Figure 1 As shown in the figure, it comprises, from top to bottom, a target layer, a standard layer, and a decision layer. Specifically, the present invention includes the following steps:

[0054] Step 1: Compare the strength of each influencing factor on the forgetting trend of English vocabulary to obtain a comparison matrix of influencing factors;

[0055] Step 2: Construct a comparison matrix of influencing factors;

[0056] Step 3: Obtain the weight matrix of influencing factors and perform a consistency check on it. If it passes the check, save the weight matrix; otherwise, repeat steps 2 and 3 until the consistency check is passed.

[0057] Step 4: For incoming English learners, first assign influencing factor scores;

[0058] Step 5: Based on fuzzy logic theory, construct a normalization function for the influencing factors and normalize the scores of the above influencing factors.

[0059] Step 6: Based on the weight matrix that passed the consistency test and the normalized influencing factor scores under different text annotation methods, obtain the estimated value of English vocabulary forgetting rate of English learners under the corresponding annotation methods.

[0060] Step 7: Compare the estimated values ​​of English vocabulary memory forgetting under different text annotation methods obtained above, and finally select the annotation method with the smallest estimated value as the best annotation method for the English learner.

[0061] It should be noted that in step 1, to minimize the forgetting of English vocabulary, different factors influence the selection of text annotation methods. These factors constitute the standard layer of the annotation method recommendation method. This invention proposes five main factors, including English proficiency (L), learning habits (H), learning ability (C), language environment (E), and mother tongue transfer (M).

[0062] It should be noted that in step 2, to quantitatively predict the different impacts of the aforementioned influencing factors on the selection of annotation methods, the weights corresponding to each influencing factor must first be obtained. Based on the subjective judgments of English learners during their actual learning process, the relative strength of the influence of each factor on vocabulary retention and forgetting is determined through pairwise comparisons, and quantitatively represented in the form of an influencing factor comparison matrix. Subsequently, an influencing factor weight matrix that satisfies the consistency test is obtained, thus providing a quantitative basis for the recommendation of annotation methods.

[0063] Therefore, we first construct a comparison matrix of influencing factors as shown in equation (1) to compare the relative strength of the influence of different influencing factors on the forgetting trend of English vocabulary. Generally, its value can be an integer between 1 and 9.

[0064]

[0065] In the above formula, L, H, C, E, and M represent English proficiency, learning habits, learning ability, language environment, and mother tongue transfer, respectively. LL c LH c LC c LE c LM These represent the relative strength of English proficiency compared to English level, learning habits, learning ability, language environment, and mother tongue transfer in influencing vocabulary memorization when choosing a text annotation method. The interpretation principles for other symbols are similar.

[0066] Based on the influencing factor comparison matrix constructed above, each column of the matrix is ​​further processed as follows:

[0067]

[0068] Summing each row of matrix (2) yields its average value. Adding a new column, we obtain the weight matrix W of each influencing factor, as shown in the following formula:

[0069] W = (w L w H w C w E w M (3)

[0070] For convenience, each element in matrix W will be denoted as w. i (i = L, H, C, E, M).

[0071] To ensure the validity of the aforementioned weight matrix of influencing factors, consistency checks are required for each weight. This is achieved through the following calculations:

[0072]

[0073] Let each element of matrix W' be denoted as w. i '(i=L,H,C,E,M), by w i 'with w i After performing the quotient operation, the largest eigenvalue of the weight matrix is ​​obtained as follows:

[0074]

[0075] It should be noted that the main purpose of step 2 is to lay the groundwork for the consistency check of the weight matrix in step 3, so as to obtain a weight matrix that satisfies the consistency check.

[0076] Subsequently, the consistency index (CI) is calculated according to the following formula (6):

[0077]

[0078] In the above formula, n is the number of terms in the weight matrix.

[0079] Finally, the consistency detection metrics are shown below:

[0080]

[0081] In equation (7), RI is the consistency detection index of any pairwise comparison matrix, and its value is related to the number of comparison items, as shown in Table 1. For this patent, 1.12 should obviously be adopted.

[0082] Table 1 Relationship between Consistency Index and Number of Items

[0083]

[0084] Finally, the obtained consistency detection index CR is compared with 0.10. If it is less than 0.10, it is considered acceptable; otherwise, it indicates that the weight matrix is ​​unreasonable, and the influencing factor comparison matrix should be reconstructed and the influencing factor weight matrix should be obtained.

[0085] It should be noted that in step 4, the English learners are first asked to rate the five influencing factors based on their own experience.

[0086] It should be noted that in step 5, the self-rating values ​​of each influencing factor are mainly normalized based on fuzzy logic. The specific steps are as follows.

[0087] After obtaining the weight matrix corresponding to the influencing factors, the impact of different annotation methods on the forgetting of English vocabulary can be predicted based on the current English learner's English proficiency (L), learning habits (H), learning ability (C), language environment (E), and mother tongue transfer (M). However, each influencing factor has different dimensions and units, requiring normalization. Therefore, this patent designs a normalization method based on fuzzy logic to normalize each influencing factor. Specifically, a normalization function with the following form is constructed:

[0088] f:(x∈R)→(x U ∈[0,1]) (8)

[0089] In the formula, x represents the variable to be normalized, f(·) represents the normalization function, and x U This indicates the influencing factors after normalization.

[0090]

[0091] Where f(·) is a general fuzzy logic membership function, and the specific values ​​of a, b, c, and d are application-dependent; thus, the current English learner (let's assume U) is obtained. i The normalized influencing factors of vocabulary forgetting are as follows:

[0092]

[0093] In the formula, This represents the self-rating scores of each influencing factor obtained in step 5. and Representing learner U i Normalized values ​​of influencing factors L, H, C, E and M.

[0094] It should be noted that the main purpose of step 6 is to obtain an estimated value of the vocabulary forgetting rate of English learners. The specific process is as follows:

[0095] The English learner U is obtained according to the following formula. i Estimated English vocabulary forgetting rate using annotation method (mo)

[0096]

[0097] In the formula, mo,mo∈{M',S',H'} indicates that the annotation method can be selected as native language annotation, English annotation, or a mixed native language and English annotation.

[0098] It should be noted that in step 7, according to (11), the English learner U can be obtained. iThe impact of three different annotation methods on the forgetting trend of English vocabulary was investigated. Finally, the annotation method that minimized the estimated forgetting rate of English vocabulary was selected as the recommended annotation method:

[0099]

[0100] On the other hand, embodiments of the present invention also provide a low-forgetting-rate English annotation recommendation system based on the AHP method, comprising:

[0101] The processor and memory are used to store program instructions, and the processor is used to call the stored instructions in the memory to execute a low-forgetting-rate English annotation recommendation method based on the AHP method as described in the above technical solution.

[0102] The English annotation method proposed in this invention aims to improve English vocabulary memorization by estimating the impact of selected annotation methods on the forgetting trend of English vocabulary. The entire system is structured into a target layer, a criterion layer, and an indicator layer. This reflects the concept of this recommendation method (and system) to measure the efficiency of English learners' annotation methods from different perspectives. To facilitate English learners in selecting suitable annotation methods, the influence weight matrix determination mechanism provided in this invention determines the influence weights of different annotation methods on the forgetting trend of English vocabulary. Based on the weights and combined with historical data from the learner's vocabulary memorization process, an annotation method recommendation threshold is obtained. Therefore, for different English learners, the optimal annotation method is determined by evaluating the influence of their annotation methods on English vocabulary memorization and comparing the influence of different annotation methods.

[0103] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for recommending low-forgetting-rate English annotation methods based on the AHP approach, characterized in that, Includes the following steps: Step 1: Identify the factors influencing the choice of English annotation methods; Step 2: Construct a comparison matrix of influencing factors; Step 3: Obtain the weight matrix of influencing factors and perform a consistency check on it. If it passes the check, save the weight matrix; otherwise, repeat steps 2 and 3 until the consistency check is passed. Step four: For the incoming English learners, first assign influencing factor scores; Step 5: Based on fuzzy logic theory, construct normalization functions for different influencing factors and normalize the scores of the above influencing factors. Step 6: Based on the weight matrix that passed the consistency check and the normalized influencing factor scores under different text annotation methods, obtain the estimated value of English vocabulary forgetting rate of English learners under the corresponding annotation method. The normalization calculation formula is as follows: (8)； In the formula, Represents the variable to be normalized. Represents the normalization function. Indicates the influencing factors after normalization; (9)； in, It is a constant; thus, we obtain the current English learners The normalized measures of factors influencing vocabulary forgetting are as follows: (10) in, For English proficiency, For study habits, For learning ability, For the language environment, For mother tongue transfer; The process for obtaining an estimated rate of forgetting of English vocabulary among English learners is as follows: English learners are obtained based on the following formula Choose annotation method Estimated English vocabulary forgetting rate at that time : (11)； In the formula, The annotation methods are indicated as native language annotation, English annotation, and mixed native language and English annotation. Step 7: Compare the estimated values ​​of English vocabulary memory forgetting under the different text annotation methods obtained above, and finally select the annotation method with the smallest estimated value as the best annotation method for the English learner.

2. The method for recommending low-forgetfulness English annotation methods based on the AHP method as described in claim 1, characterized in that: The influencing factors in step one include: English proficiency. Study habits Learning ability Language environment and mother tongue transfer .

3. The method for recommending low-forgetfulness English annotation methods based on the AHP method as described in claim 1, characterized in that: The comparison matrix of influencing factors in step two is as follows: (1) In the above formula, , , 、 and These respectively represent English proficiency, learning habits, learning ability, language environment, and mother tongue transfer. These represent the relative strength of English proficiency compared to English level, learning habits, learning ability, language environment, and mother tongue transfer in influencing vocabulary memorization when choosing a text annotation method. The interpretation principle for other symbols is the same.

4. The method for recommending low-forgetfulness English annotation methods based on the AHP method as described in claim 3, characterized in that: Based on the constructed comparison matrix of influencing factors, each column of the comparison matrix is ​​processed as follows: (2)； Summing each row of matrix (2) and then obtaining its average value yields the weight matrix of influencing factors. As shown in the following formula: (3)； For convenience, the weight matrix of influencing factors is shown. The elements in are denoted as ,in, For English proficiency, For study habits, For learning ability, For the language environment, This is due to mother tongue transfer.

5. The method for recommending low-forgetfulness English annotation methods based on the AHP method as described in claim 4, characterized in that: To perform a consistency check on each weight in the influencing factor weight matrix, the following calculations are performed: (4)； matrix The elements in are denoted as ,Will and After performing quotient calculations, the largest eigenvalue of the influencing factor weight matrix is ​​obtained as follows: (5)； Subsequently, the consistency index is calculated according to the following formula (6). : (6)； In the above formula, The number of terms in the weight matrix; Finally, the consistency test index of equation (7) is obtained. : (7)； in, It is a constant.

6. The method for recommending low-forgetfulness English annotation methods based on the AHP method as described in claim 1, characterized in that: The annotation method corresponding to the lowest estimated rate of forgetting of English vocabulary was selected as the best recommended annotation method. ,Right now: (12)。 7. A low-forgetting-rate English annotation recommendation system based on the AHP method, characterized in that, include: A processor and a memory, wherein the memory is used to store program instructions, and the processor is used to call the stored instructions in the memory to execute a low-forgetting-rate English annotation recommendation method based on any one of claims 1-6.

Images