No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Text Mining an Automatic Short Answer Grading (ASAG), Comparison of Three Methods of Cosine Similarity, Jaccard Similarity and Dice's Coefficient
... Research has shown that LSA was useful to reduce vectorized texts and keep the answer context in the dataset. In the study conducted by Henderi et al. (2021) and Stefanovič et al. (2019) the cosine measure has also been applied to find the similarity between the short texts of the students' answers. In both investigations, the Dice coefficient and the Jaccard measure have been used. ...
... In both investigations, the Dice coefficient and the Jaccard measure have been used. Henderi et al. (2021) analyze the performance and effectiveness of three similarity measures (cosine, Dice, and Jaccard) in automatic answer grading. The research results were evaluated by calculating the correlation. ...
The public availability of large language models, such as chatGPT, brings additional possibilities and challenges to education. Education institutions have to identify when large language models are used and when text is generated by the student itself. In this paper, chatGPT usage in students' answers is investigated. The main aim of the research was to build a machine learning model that could be used in the evaluation of students' answers to open-ended questions written in the Lithuanian language. The model should determine whether the answers were originally written students or answered with the help of chatGPT. A new dataset of student answers has been collected in to train machine learning models. The dataset consists of original student answers, chatGPT answers, and paraphrased chatGPT answers. A total of more than 1000 answers have been prepared. 24 combinations of text pre-processing algorithms have been analyzed. In text pre-processing, the main focus was on various tokenization methods, such as the Bag of Words and Ngrams, the stemming algorithm, and the stop words list. For the analyzed dataset, these pre-processing methods were more effective than application of multilanguage BERT for document embedding. Based on the features/properties of the dataset, the following learning algorithms have been investigated: artificial neural networks, decision trees, random forest, gradient boosting trees, k-nearest neighbours, and naive Bayes. The main results show that the highest accuracy of 87% in some cases can be obtained using gradient boosting trees, random forests, and artificial neural network algorithms. The lowest accuracy has been obtained using the k-nearest neighbouring algorithm. Furthermore, the results of experimental research suggest that the usage of chatGPT in student answers can be automatically identified.
... VIF analysis evaluates the level of multicollinearity among the predictor variables in a regression model by calculating the variance ratio of each coefficient of an independent variable to the variance of a coefficient that would be obtained if that variable was uncorrelated with the other predictors. The use of VIF to examine common method bias is unconventional, as VIF is traditionally employed to assess multicollinearity in regression analysis, not to specifically address issues related to the systematic variance introduced by the data collection method (Wahyuningsih, 2021). In this study, multicollinearity among the constructs was assessed using VIF analysis ( Table 2). ...
... The proposed hypotheses were rigorously tested using a PLS model (Chi, 2021;Endsuy, 2021;Ringle et al., 2009;Wahyuningsih, 2021). The results presented in Table 6 are convincing and provide strong evidence for the validity of the proposed hypotheses. ...
... In order to enhance the uniqueness of the gathered ideas, the mea cosine or Jaccard similarity might be used [26,27], but this would be a topic for further implementation of the "kresilnik" tool. Figure 3 shows the design of the hybrid [28][29][30][31][32] human-OpenAI tool for gen ideas, which is named "kresilnik". The system consists of the server-side infrast the OpenAI API, and the user interface. ...
... During the review of ideas within a particular category, redundant ideas may be excluded, although this decision falls within the purview of the expert group. In order to enhance the uniqueness of the gathered ideas, the measures of cosine or Jaccard similarity might be used [27,28], but this would be a topic for possible further implementation of the "kresilnik" tool. Figure 3 shows the design of the hybrid [29][30][31][32][33] human-OpenAI tool for generating ideas, which is named "kresilnik". ...
A modification of the brainstorming process by the application of artificial intelligence (AI) was proposed. Here, we describe the design of the software system “kresilnik”, which enables hybrid work between a human group and AI. The proposed system integrates the Open AI-GPT-3.5–turbo model with the server side providing the results to clients. The proposed architecture provides the possibility to not only generate ideas but also categorize them and set priorities. With the developed prototype, 760 ideas were generated on the topic of the design of the Gorenjska region’s development plan with eight different temperatures with the OpenAI-GPT-3.5-turbo algorithm. For the set of generated ideas, the entropy was determined, as well as the time needed for their generation. The distributions of the entropy of the ideas generated by the human-generated and the AI-generated sets of ideas of the OpenAI-GPT-3.5–turbo algorithm at different temperatures are provided in the form of histograms. Ideas are presented as word clouds and histograms for the human group and the AI-generated sets. A comparison of the process of generating ideas between the human group and AI was conducted. The statistical Mann-Whitney U-test was performed, which confirmed the significant differences in the average entropy of the generated ideas. Correlations between the length of the generated ideas and the time needed were determined for the human group and AI. The distributions for the time needed and the length of the ideas were determined, which are possible indicators to distinguish between human and artificial processes of generating ideas.
... Knowledge sharing allows for the benefit of knowledge gained by Irum and Pandey [13]. The main reason for sharing individual knowledge with the entire organization is that the knowledge should not disappear if that employee leaves the organization [15]. The organization must put some measures (incentives) in place to ensure knowledge sharing and discourage hoarding and monopoly. ...
... Once knowledge is shared between people in organizations, the shared knowledge must be applied to solve a problem. According to Wahyuningsih [15], if the knowledge that is collected, stored, created and shared is not applied properly, the whole process will be in vain and for proper knowledge application, the knowledge management process must be communicated to users. That is, knowledge must be put to effective and efficient use to fill a gap or a need. ...
This study aimed at identifying the role of knowledge management in raising the efficiency of the performance of the administrative body at King Abdulaziz University. In light of this goal, a number of hypotheses were developed and tested by preparing a questionnaire comprising two variables, namely knowledge management (information technology, organizational culture, organizational structure) and the performance of the administrative body (personal elements, performance elements, knowledge of job requirements). This study was conducted at King Abdulaziz University. The necessary information was obtained through the questionnaire tool prepared for this purpose. Data were collected from 304 individuals of the administrative body of King Abdulaziz University. The results were analyzed using correlation and regression analyzes of the SPSS program. The snowball sample method was relied upon, and the link was sent to a number of the administrative body with a recommendation for them to distribute it among their university colleagues. In light of this, 315 responses were obtained, 11 responses were excluded because they were not valid. Consequently, the responses valid for analysis were 304 questionnaires. Then the student concluded with a set of recommendations related to the research variables.
... During the text mining process, raw data is meaningless and of no use. It is necessary to process the raw data before it can be read by a computer [5]. Preprocessing is the name given to the method that is used to process the raw data itself [6]. ...
... The process of separating a piece of text into its component sentences is known as tokening [5]. Table 3 illustrates an application of tokening that was performed for the purpose of this research. ...
CS is one of the most important functions of any client-related organization, whether a business or a school (customer service). Notably from the committee responsible for student selection, CS, on the other hand, has a very limited capacity to be handled by humans, which can reduce university satisfaction. Therefore, we require technological assistance, which in this case takes the form of an AI-based chatbot. The objective of this study is to design and develop a chatbot system utilizing NLP (natural language processing) to aid the CS of the new student admissions committee at Pahlawan Tuanku Tambusai University in answering questions from prospective new students. The employed method is dice similarity weighted by TFIDF. The results of the conducted tests indicated that the recall rate was 100 percent and the precision reached 76.92 percent. The evaluation results indicate that the chatbot can effectively respond to questions from prospective students.
... As another attempt, a comparison analysis is undertaken by Parsania et al. [15] to determine the best data mining classification approaches based on healthcare data in terms of accuracy, sensitivity, precision, false-positive rate, and f-measure. Naïve Bayes, Bayesian Network, J RIPPER (JRip), OneRule (OneR), and PART methods are selected to be used on a dataset from a health database. ...
... Results in[4] tells that the NB method is more accurate than J48 DT to categorize agriculture datasets since it classifies 98 percent of occurrences correctly. An experiment is undertaken in the health domain to classify 3163 patients' data as indicated in[15]. Naïve Bayes (NB), Bayesian Network (BayesNet), J Ripper (JRip), One Rule (OneR), and PART classification methods are utilized. ...
Many business applications rely on their history data to anticipate their company future. The marketing products process is one of the essential procedures for the firm. Customer needs supply a useful piece of information that helps to promote the suitable products at the proper moment. Moreover, services are recognized recently as products. The development of education and health services is reliant on historical data. For the more, lowering online social media networks problems and crimes need a big supply of information. Data analysts need to utilize an efficient categorization system to predict the future of such businesses. However, dealing with a vast quantity of data demands tremendous time to process. Data mining encompasses numerous valuable techniques that are used to anticipate statistical data in a number of business applications. The classification technique is one of the most extensively utilized with a range of algorithms. In this work, numerous categorization methods are revised in terms of accuracy in diverse domains of data mining applications. A complete analysis is done following delegated reading of 20 papers in the literature. This study intends to allow data analysts to identify the best suitable classification algorithm for numerous commercial applications including business in general, online social media networks, agriculture, health, and education. Results reveal FFBPN is the best accurate algorithm in the business arena. The Random Forest algorithm is the most accurate in categorizing online social networks (OSN) activity. Naïve Bayes method is the most accurate to classify agriculture datasets. OneR is the most accurate method to classify occurrences inside the health domain. The C4.5 Decision Tree method is the most accurate to classify students’ records to forecast degree completion time.
... Sahu & Bhowmick [12] demonstrate that grading student responses is improved by combining various graph alignment criteria with lexical semantic similarity metrics. There are several methods and techniques used to measure text similarity, including Cosine similarity, as discussed by Rosnelly et al. [13], Jaccard similarity, and the Dice Coefficient, outlined by Wahyuningsih et al. [14]. Additionally, edit distance, as studied by Anbananthen et al. [15], and Latent Semantic Analysis (LSA), as described by Kaur & Sasi [16], are utilized for this purpose. ...
Automated subjective assessment presents a significant challenge due to the complex nature of human language and reasoning characterized by semantic variability, subjectivity, language ambiguity, and judgment levels. Unlike objective exams, subjective assessments involve diverse answers, posing difficulties in automated scoring. The paper proposes a novel approach that integrates advanced natural language processing (NLP) techniques with principled grading methods to address this challenge. Combining Transformer-based Sequence Language Modeling with sophisticated grading mechanisms aims to develop more accurate and efficient automatic grading systems for subjective assessments in education. The proposed approach consists of three main phases: Content Summarization: Relevant sentences are extracted using self-attention mechanisms, enabling the system to effectively summarize the content of the responses. Key Term Identification and Comparison: Key terms are identified within the responses and treated as overt tags. These tags are then compared to reference keys using cross-attention mechanisms, allowing for a nuanced evaluation of the response content. Grading Process: Responses are graded using a weighted multi-criteria decision method, which assesses various quality aspects and assigns partial scores accordingly. Experimental results on the SQUAD dataset demonstrate the approach’s effectiveness, achieving an impressive F-score of 86%. Furthermore, significant improvements in metrics like ROUGE, BLEU, and METEOR scores were observed, validating the efficacy of the proposed approach in automating subjective assessment tasks. Doi: 10.28991/HIJ-2024-05-03-06 Full Text: PDF
... The process focused on retaining nouns, verbs, adjectives, and adverbs while excluding other grammatical classes such as determiners and prepositions to refine the analyzed content (Wahyuningsih et al., 2021). After the process, the lemmas of each document were combined into continuous texts, preparing the dataset for the vectorization stage. ...
Collaboration between the public and private sectors is crucial for supporting resource-constrained government budgets globally. Over the past two decades, studies have recorded significant advances in public-private partnerships (PPPs). However, PPPs in agribusiness within Latin America and the Caribbean (LAC) remain underexplored. This study analyzes the primary issues related to PPPs in agribusiness across selected countries and compares sentiments regarding these partnerships within the analyzed countries. Using text mining, topic modeling, and sentiment analysis, the study found that the main issues revolve around infrastructure, impacting trade, flow, and services in regional, national, and continental agribusiness and exports. While PPPs are seen as an innovative approach to improving public services, sentiment analysis reveals that many countries express anger and disgust, primarily due to concerns about corruption and the state’s inability to manage or play an effective role in these public policies. This study highlights that integrating topic and sentiment data offers a comprehensive view that can inform more effective public policies and development strategies for PPPs in agribusiness.
... Algoritma Jaccard merupakan salah satu algoritma text mining. Algoritma Jaccard merupakan salah satu metode yang bisa digunakan untuk menghitung kemiripan antara 2 objek atau item [24], [17], [25], [26]. Nilai kemiripan Algoritma Jaccard berkisar antara 0% hingga 100% [27]. ...
Choosing an unique dissertation title is a challenge. The number of dissertation titles rises as the number of students increases. The title of the dissertation must differ between students. Anticipation that can be done is to adopt a similarity algorithm to detect similarities in dissertation titles. The similarity algorithm chosen is the Jaccard Similarity Algorithm. Jaccard algorithm can be used to detect document similarities. Analysis process begins with preprocessing text. The stages of preprocessing text are case folding, tokenizing, stop word removal and stemming. In this study, variations of stop word removal were tested and the accuracy results obtained were tested after being analyzed using Jaccard Similarity. Researchers call it Stop Word Removal Version One (SWR1) and Stop Word Removal Version Two (SWR2). In SWR1 only prepositions and conjunctions are deleted. Meanwhile SWR2; what was done was the deletion of words in SWR1 plus the deletion of words that were often used in the title but did not make a significant contribution to the meaning of the title. The aim of this approach is to test the accuracy produced by Jaccard against these two stop word removal approaches. The research results show that Jaccard accuracy with SWR2 has an accuracy of 97.8% and SWR1 accuracy is 57.7%. stop word removal , is a critical stage in determining similarity and has a significant influence on the results of the Jaccard Algorithm.
... This algorithm calculates the similarity between two objects (items) [47]. As with the distance cosine and matching coefficient, in general, the calculation of this method is based on the similarity of the size vector space [48]. Query in Figure 3 explains how we collect the ingredients of each product before performing the Jaccard similarity. ...
... Research [7] also uses the same object, ARI, but uses a classification method to detect ARI disease. Research [8] compare Cosine Similarity, Jaccard Similarity and Dice Coefficient for automatic assessment of short answers with questions and answers in Indonesian. This study shows that the cosine similarity method is able to obtain the highest correlation. ...
Medical Information Retrieval (Med-IR )is part of computer science that discusses the search for a medical document. Medical Information Retrieval is needed by patients to know the initial prediction of the symptoms they are experiencing. ARI (Acute Respiratory Infection) is a disease that almost everyone has experienced which can cause death. This study uses a dataset of ARI sufferers and user queries that contain symptoms in text form. Furthermore, the query data is processed with the Med-IR application using Bi-Gram, TF-IDF as the feature extraction and Cosine Similarity as the similarity method, so that a return document is produced which is expected to be used as an early prediction of ARI in patients. The research also uses a critical disease wighting process, so that the results of the Med-IR are complemented by predictions of the severity level of the disease. From the results of research conducted at the Assyafi'u Sentosa Lengkong Clinic, Nganjuk, the best results were obtained for precision values of 85.5% and 52.9% for recall values . The evaluation of disease severity with Mean Absolute Percentage Error (MAPE) getting a low score of 2,529%. Keyword : Medical Information Retrieval, ARI, Weighting critical disease, Bi-Gram, TF-IDF, Cosine Similarity.
... State of the art of previous research has discussed text similarity detection with many methods used for weighting a text, including Rabin-Karp, winnowing, Smith-Waterman and Manber, and TF [10]- [12]. In addition, algorithms used to find similarity scores, including Jaccard, dice similarity, neural network, and cosine similarity, are considered to have better similarity rates [13]. Reference [14] has investigated the collaborative use of the cosine similarity method with other weighting algorithms, such as artificial neural network (ANN) and support vector machine (SVM). ...
Plagiarisme adalah tindakan meniru dan mengutip bahkan menyalin atau mengakui hasil karya orang lain sebagai hasil karya diri sendiri. Tugas akhir merupakan salah satu syarat wajib mahasiswa untuk menyelesaikan pembelajaran pada perguruan tinggi. Tugas akhir harus disusun mahasiswa berdasarkan ide sendiri. Akan tetapi, banyak terjadi plagiarisme karena mudahnya melakukan kegiatan tersebut, yaitu hanya dengan menyalin teks gagasan orang lain kemudian ditempelkan dalam lembar kerja dan diakui bahwa gagasan tersebut adalah ide sendiri. Selain itu, mengganti beberapa kata dalam kalimat gagasan orang lain dengan gaya bahasa sendiri tanpa menuliskan sumber aslinya juga termasuk plagiarisme. Pengecekan tugas akhir yang masih manual juga menjadi masalah bagi koordinator tugas akhir, yang membutuhkan ketelitian tinggi dan waktu yang cukup banyak untuk mengecek plagiarime pada dokumen tugas akhir. Maka, deteksi plagiarisme sangat dibutuhkan untuk mencegah tindakan plagiarisme makin berkembang. Menyikapi hal tersebut, penelitian ini bermaksud mengembangkan sistem yang dapat mendeteksi persamaan antardokumen teks yang berfokus pada kata yang mengandung sinonim pada suatu kalimat. Salah satu algoritma yang digunakan adalah synonym recognition, yang berfungsi untuk mendeteksi kata yang mengandung sinonim, dengan proses membandingkan setiap kata dengan kata yang terdapat pada kamus. Synonym recognition dikombinasikan dengan metode winnowing, yang berfungsi untuk pembobotan teks berbasis fingerprint. Setelah diperoleh bobot dari masing-masing dokumen, tingkat kemiripan antardokumen dihitung dengan algoritma cosine similarity. Hasil rata-rata nilai kemiripan untuk deteksi judul dan abstrak dengan menambahkan synonym recognition meningkat sebesar 3,11% daripada tanpa menggunakan synonym recognition yang dikombinasikan dengan metode pembobotan winnowing. Hasil pengujian menunjukkan bahwa algoritma-algoritma yang digunakan akurat dengan pengujian akurasi dan root mean squared error (RMSE).
... As mentioned earlier, the cosine similarity algorithm gives the most accurate results over other algorithms on multibyte Unicode Bengali text. However, the Jaccard similarity algorithm [32] is also the closest performing algorithm for Bengali texts. Table 3 illustrates the proportion of similarity between articles 1 and 2. The cosine similarity algorithm gives more precise results than the Jacquard similarity. ...
Plagiarism is an act of literature fraud, which is presenting others’ work or ideas without giving credit to the original work. All published and unpublished written documents are under the cover of this definition. Plagiarism, which increased significantly over the last few years, is a concerning issue for students, academicians, and professionals. Due to this, there are several plagiarism detection tools or software available to detect plagiarism in different languages. Unfortunately, negligible work has been done and no plagiarism detection software available in the Bengali language where Bengali is one of the most spoken languages in the world. In this paper, we have proposed a plagiarism detection tool for the Bengali language that mainly focuses on the educational and newspaper domain. We have collected 82 textbooks from the National Curriculum of Textbooks (NCTB), Bangladesh, scrapped all articles from 12 reputed newspapers and compiled our corpus with more than 10 million sentences. The proposed method on Bengali text corpus shows an accuracy rate of 97.31%
... Stopwords removal (filtering) is removing words that occur frequently but have no meaning [18] [6]. Prepositions and conjunctions are also included in stopwords removal. ...
This study aims to measure the similarity of the answers to the description by using alternative answers as reference answers provided by the lecturer with a view to overcoming the diversity of student answers. This research focuses more on Indonesian language questions and answers by combining the jaccard similarity algorithm and keyword similarity. The results obtained indicate that by adding alternative reference answers, it can increase the correlation value to 0.78% and reduce MAE to 0.55. Likewise, after combining the jaccard similarity algorithm and keyword similarity, the correlation value increased to 0.78% and MAE decreased to 0.49.
... Many types of medical equipment require consumables and accessories. Therefore, in conjunction with the medical equipment inventory, the healthcare facility should maintain a separate inventory of consumables necessary to operate medical equipment [9]. These include items such as blood tubing sets, electrodes, electrocardiographic (ECG) paper, conductive gel and reagents. ...
Extracting data or an effort to retrieve valuable knowledge and information in a large database is called data mining or Knowledge Discovery in Database or usually shortened as KDD . One of the most popular algorithm in data mining technic is Apriori Algorithm, while the discovery of “relational combination pattern among itemset used Association Rules”. Data mining has been implemented into the various fields like : business or trade, education and telecommunication. In business for instance, the implementation result of data mining use ‘algorithm Apriori which can give a hand to help the Businessmen make decision on supplies. For example, the necessity of supplies system in a drugstore as one of the medical stuff supplier, and to determine which product as the priority should be supplied to anticipate out of stock of supplies availability in the store, as the results will also affect to the consumer service and daily income. Medical tools are essential unit should be supplied and being and essential factor which will impact to the consumer trust to a hospital or another medical service. That is why the availability of medical tools in drugstores is completely needed to support the success of distribution to the consumers, so the activity of medical service to consumers run thoroughly. In this case, data mining is seen as able to built intelligent business environment as solution for competing increated competition among the drugstores in future.
... Every feature of the new dataset is compared to the features of the old datasets regarding the syntactic and the semantic similarity of the features, as well as the characteristics of the features. In order to compute the syntactic similarity, a variety of techniques are utilized, including Jaccard similarity [31] and Cosine similarity [32]. Regarding the semantic similarity, a more complex technique is used that is based on Transformers [33]. ...
Data Cleaning is a subfield of Data Mining that is thriving in the recent years. Ensuring the reliability of data, either when generated or received, is of vital importance to provide the best services possible to users. Accomplishing the aforementioned task is easier said than done, since data are complex, generated at an extremely high rate and are of enormous size. A variety of techniques and methods that are part of other subfields from the domain of the Computer Science have been invoked to assist in making Data Cleaning the most efficient and effective possible. Those subfields include, among others, Natural Language Processing (NLP), which in essence refers to the interaction among computers and human language, seeking to find a way to program computers to be able to process and analyze huge volumes of human language data. NLP is a concept that exists for a long time, but, as time goes by, it is proposed that it can be applied to a variety of concepts that are not solely NLP-related. In this paper, a rule-based data cleaning mechanism is proposed, which utilizes NLP to ensure data reliability. Making use of NLP enabled the mechanism not only to be extremely effective but also to be a lot more efficient compared to other corresponding mechanisms that do not utilize NLP. The mechanism was evaluated upon diverse healthcare datasets, not however being limited to the healthcare domain, but supporting a generalized data cleaning concept.
... Every feature of the new dataset is compared to the features of the old datasets regarding the syntactic and the semantic similarity of the features, as well as the characteristics of the features. The computation of the syntactic similarity takes place by utilizing two commonly used techniques for accomplishing such task, namely the Jaccard similarity [82] and the Cosine similarity [83]. Regarding the semantic similarity, a more complex technique is used that is based on Transformers, which are types of Deep Learning (DL) models that differentially weight the input data [84]. ...
Extracting useful knowledge from proper data analysis is a very challenging task for efficient and timely decision-making. To achieve this, there exist a plethora of machine learning (ML) algorithms, while, especially in healthcare, this complexity increases due to the domain’s requirements for analytics-based risk predictions. This manuscript proposes a data analysis mechanism experimented in diverse healthcare scenarios, towards constructing a catalogue of the most efficient ML algorithms to be used depending on the healthcare scenario’s requirements and datasets, for efficiently predicting the onset of a disease. To this context, seven (7) different ML algorithms (Naïve Bayes, K-Nearest Neighbors, Decision Tree, Logistic Regression, Random Forest, Neural Networks, Stochastic Gradient Descent) have been executed on top of diverse healthcare scenarios (stroke, COVID-19, diabetes, breast cancer, kidney disease, heart failure). Based on a variety of performance metrics (accuracy, recall, precision, F1-score, specificity, confusion matrix), it has been identified that a sub-set of ML algorithms are more efficient for timely predictions under specific healthcare scenarios, and that is why the envisioned ML catalogue prioritizes the ML algorithms to be used, depending on the scenarios’ nature and needed metrics. Further evaluation must be performed considering additional scenarios, involving state-of-the-art techniques (e.g., cloud deployment, federated ML) for improving the mechanism’s efficiency.
... Matthews and Visagie [26] provide a proposal for reducing collection transfer times in order to obtain an adequate arrangement for SKU collection activities in a warehouse. Faia Pinto and Nagano [27] offer GA-OPS, a computational tool based on two genetic algorithms that reduces the number of picking trips while matching the constraints specified in different production orders. ...
The latent demand to optimize costs and customer service has been fostered in the current economic situations, characterized by high competitiveness and disruption in supply chains, placing inventories as a vital sector with significant potential to implement improvements in firms. Inventory management that is done correctly has a favorable impact on logistics performance indexes. Warehousing operations account for around 15% of logistics expenditures in terms of dollars. This article employs a method based on the Partitioning Around Medoids algorithm that incorporates, in a novel way, the application of a strategy for locating the optimal picking point based on cluster classification, taking into account the qualitative and quantitative factors that have the greatest impact or priority on inventory management in the company. The results obtained with this model improve the routes of distributed materials based on the identification of their characteristics such as the frequency of collection and handling of materials, allowing for the reorganization and expansion of storage capacity of the various SKUs, moving from a classification by families to a cluster classification. This article shows a suggestion for a warehouse distribution design using data mining techniques, which uses indicators and key qualities for operational success for a case study in a corporation, as well as an approach to improve inventory management decision-making.
... Many types of medical equipment require consumables and accessories. Therefore, in conjunction with the medical equipment inventory, the healthcare facility should maintain a separate inventory of consumables necessary to operate medical equipment [9]. These include items such as blood tubing sets, electrodes, electrocardiographic (ECG) paper, conductive gel and reagents. ...
The pattern of the need for drugs and medical devices in various hospitals has a tendency to be repeated and similar in a relatively long period of time, especially in one particular department, because the cases found are often similar or even similar. Ensuring the availability of stock in each departmental depot is very vital, because the procurement of medical devices must go through a certain process and time, so that cases of critical rheumatism often occur but the equipment needed at depositors does not meet the standards. need or run from inventory and must indent first. By calculating the trend of demand patterns and needs using an algorithm (Apriori Association) in the dataset, a rule is formed that in the pattern of dependence between itemsets that have supporting criteria in the form of 33.3% support and 85% Confidence, where the items that appear are items with frequency of occurrence and associations so that it can be taken into consideration to ensure the availability of drugs and medical devices.
Purpose
This study aims to explore the relationship between wine label content and consumer reviews on Vivino, focusing on how label information compares to consumer perceptions and purchase decisions.
Design/methodology/approach
The research uses text mining, image mining and topic modeling techniques to analyze a data set of 444 highly rated Portuguese wines and 993,945 consumer reviews from Vivino. It examines the overlap between topics discussed in consumer reviews and the information provided on wine labels.
Findings
The findings reveal that wine labels have a limited similarity with consumer reviews. While consumer reviews primarily emphasize sensory characteristics like fruitiness and tannins, wine labels focus more on descriptive and technical information.
Originality/value
This research provides new insights into the dynamic relationship between wine labeling and consumer behavior. By analyzing the alignment between traditional wine labels and online consumer reviews, the study offers valuable implications for wineries seeking to optimize label design to match consumer preferences, particularly sensory attributes better. This study extends existing research and highlights critical gaps in how wine labels convey essential sensory information to consumers.
A recent adversarial collaboration integrated dimensions proposed in five major theories of social evaluation into two overarching dimensions: Horizontal and Vertical. This paper examines the convergence in how evaluative dimensions have been operationalized for each model to determine if they address the same constructs. Across various coding strategies and using two similarity indexes, we found robust evidence of low convergence in the traits used to operationalize dimensions assumed to represent the same constructs. These results suggest that the integration proposed by the adversarial collaboration might be limited, as it is unclear whether dimensions within the Horizontal and Vertical domains correspond to the same constructs. We discuss the theoretical and methodological implications and propose recommendations for refining construct operationalization.
Questions are crucial expressions in any language. Many Natural Language Processing (NLP) or Natural Language Understanding (NLU) applications, such as question-answering computer systems, automatic chatting apps (chatbots), digital virtual assistants, and opinion mining, can benefit from accurately identifying similar questions in an effective manner. We detail methods for identifying similarities between Arabic questions that have been posted online by Internet users and organizations. Our novel approach uses a non-topical rule-based methodology and topical information (textual similarity, lexical similarity, and semantic similarity) to determine if a pair of Arabic questions are similarly paraphrased. Our method counts the lexical and linguistic distances between each question. Additionally, it identifies questions in accordance with their format and scope using expert hypotheses (rules) that have been experimentally shown to be useful and practical. Even if there is a high degree of lexical similarity between a When question (Timex Factoid—inquiring about time) and a Who inquiry (Enamex Factoid—asking about a named entity), they will not be similar. In an experiment using 2200 question pairs, our method attained an accuracy of 0.85, which is remarkable given the simplicity of the solution and the fact that we did not employ any language models or word embedding. In order to cover common Arabic queries presented by Arabic Internet users, we gathered the questions from various online forums and resources. In this study, we describe a unique method for detecting question similarity that does not require intensive processing, a sizable linguistic corpus, or a costly semantic repository. Because there are not many rich Arabic textual resources, this is especially important for informal Arabic text processing on the Internet.
Research towards creating systems for automatic grading of student answers to quiz and exam questions in educational settings has been ongoing since 1966. Over the years, the problem was divided into many categories. Among them, grading text answers were divided into short answer grading, and essay grading. The goal of this work was to develop an ML-based short answer grading system. I hence built a system which uses finetuning on Roberta Large Model pretrained on STS benchmark dataset and have also created an interface to show the production readiness of the system. I evaluated the performance of the system on the Mohler extended dataset and SciEntsBank Dataset. The developed system achieved a Pearsons Correlation of 0.82 and RMSE of 0.7 on the Mohler Dataset which beats the SOTA performance on this dataset which is correlation of 0.805 and RMSE of 0.793. Additionally, Pearsons Correlation of 0.79 and RMSE of 0.56 was achieved on the SciEntsBank Dataset, which only reconfirms the robustness of the system. A few observations during achieving these results included usage of batch size of 1 produced better results than using batch size of 16 or 32 and using huber loss as loss function performed well on this regression task. The system was tried and tested on train and validation splits using various random seeds and still has been tweaked to achieve a minimum of 0.76 of correlation and a maximum 0.15 (out of 1) RMSE on any dataset.
Plagiarisme adalah tindakan penyalahgunaan, pencurian/perampasan, penerbitan, pernyataan, atau menyatakan sebagai milik sendiri sebuah pikiran, ide, tulisan, atau ciptaan yang sebenarnya milik orang lain. Plagiat atau biasa disebut penjiplakan adalah sebuah masalah yang cukup signifikan pada akademisi di perguruan tinggi. Hal plagiat yang biasanya dilakukan terhadap konten digital adalah melakukan copy-paste, quote, dan revisi terhadap dokumen asli. Untuk mengantisipasinya, dibutuhkan suatu cara yang dapat menganalisis teknik-teknik plagiat yang dilakukan. Ada beberapa pendekatan yang bisa diambil, salah satunya dengan menggunakan algoritma Rabin-Karp dengan metode Rolling Hash. Pendeteksian plagiarisme menggunakan algoritma Rabin-Karp dengan metode rolling hash ini diimplementasikan ke dalam program atau aplikasi untuk menentukan nilai tingkat akurasi dengan nilai presentase.
Todays there are more applications supporting Alqurán to facilitate such a study, which could be called digital AL-Quran. But when using applications digital AL-Quran, which has many applications users experience difficulties when searching for a word that users want.This occurs when users misspell a word you want to search and applications that are not yet able to identify or justify the wrong word. In this thesis made the information retrieval system that is used to find information that is relevant to the needs of its users automatically based on conformity to the query of a collection of information.Algoritma used to determine the similarity (degree of similarity) or relevant similarity algoritma, cosine, Jaccard, and nearest neighbor (k-nn) for comparing algoritma that are more relevant to the translation application alquran. The test result proves that the cosine similarity algoritma has the highest value with the percentage of 41% compared with Jaccard 19% algoritma and nearest neighbor (k-nn) 40% on translation of AL-Quran as much 6326 document and 33 query different experiments.
A B S T R A K Peringkasan dokumen berita Bahasa Indonesia dapat membantu untuk menemukan ide-ide pokok atau informasi penting lain dari sebuah berita. Berita umumnya terdiri atas banyaknya paragraf menjadi sebab diperlukan sebuah sistem untuk mengekstrak informasi, sehingga mampu memberikan ide pokok atau informasi penting yang tepat kepada pembaca, tanpa harus membaca secara detail keseluruhan isi berita tersebut, di samping itu dapat dimanfaatkan guna keperluaan Really Simple Syndication Feed (RSS-Feed). Penelitian ini memaparkan peringkasan dokumen berita berbahasa Indonesia menggunakan metode Cross Latent Semantic Analysis (CLSA) dan Latent Semantic Analysis (LSA). Untuk menguji seberapa baik hasil ringkasan yang dilakukan CLSA penelitian ini menggunakan 240 artikel berita yang diambil dari halaman portal www.kompas.com dan dua pakar yang berlatar belakang bidang yang berbeda. Hasil ringkasan CLSA dengan compression rate 30% memperoleh nilai F-Measure 0.72%. Penelitian ini juga menemukan fakta bahwa CLSA lebih baik dari metode LSA yang merupakan cikal bakal dari metode CLSA, walaupun skor hasil F-Measure keduanya tidak berbeda jauh.Kata kunci: Berita, Cross latent semantic analyisis, Latent semantic analysis, peringkasan dokumen, RSS-Feed. A B S T R A C T Summarizing news documents in Bahasa serves to find main ideas or any other important information from a piece of news. A system to extract the information from ones consisting of many paragraphs is then deemed necessary in order to present precise main ideas or important information to the readers without them having to read the entire passage of news documents, in addition to become useful for Really Simple Syndication Feed (RSS-Feed). This article discusses summarizing news documents in Bahasa using Cross Latent Semantic Analysis (CLSA). To test if the summary resulted from CLSA qualified, this study examines 240 news articles retrieved from www.kompas.com and employs two experts from different fields. The summary resulted from CLSA with a compression rate of 30% obtains an F-Measure of 0.72%. This study also evidently indicates that CLSA has better performance from Latent Semantic Analysis (LSA) which was the initial system for CLSA, despite both F-Measure percentages being only slightly different.Keywords: Cross latent semantic analysis, Document summarization, Latent semantic analysis, News, RSS-Feed.
Most automatic scoring systems use pattern based that requires a lot of hard and tedious work. These systems work in a supervised manner where predefined patterns and scoring rules are generated. This paper presents a different unsupervised approach which deals with students’ answers holistically using text to text similarity. Different String-based and Corpus-based similarity measures were tested separately and then combined to achieve a maximum correlation value of 0.504. The achieved correlation is the best value achieved for unsupervised approach Bag of Words (BOW) when compared to previous work.
A bug-tracking system such as Bugzilla contains bug reports (BRs) collected from various sources such as development teams, testing teams, and end users. When bug reporters submit bug reports to a bug-tracking system, the bug reporters need to label the bug reports as security bug reports (SBRs) or not, to indicate whether the involved bugs are security problems. These SBRs generally deserve higher priority in bug fixing than not-security bug reports (NSBRs). However, in the bug-reporting process, bug reporters often mislabel SBRs as NSBRs partly due to lack of security domain knowledge. This mislabeling could cause serious damage to software-system stakeholders due to the induced delay of identifying and fixing the involved security bugs. To address this important issue, we developed a new approach that applies text mining on natural-language descriptions of BRs to train a statistical model on already manually-labeled BRs to identify SBRs that are manually-mislabeled as NSBRs. Security engineers can use the model to automate the classification of BRs from large bug databases to reduce the time that they spend on searching for SBRs. We evaluated the model's predictions on a large Cisco software system with over ten million source lines of code. Among a sample of BRs that Cisco bug reporters manually labeled as NSBRs in bug reporting, our model successfully classified a high percentage (78%) of the SBRs as verified by Cisco security engineers, and predicted their classification as SBRs with a probability of at least 0.98.
Approximate matching of strings is reviewed with the aim of surveying techniques suitable for finding an item in a database when there may be a spelling mistake or other error in the keyword. The methods found are classified as either equivalence or similarity problems. Equivalence problems are seen to be readily solved using canonical forms. For sinuiarity problems difference measures are surveyed, with a full description of the wellestablmhed dynamic programming method relating this to the approach using probabilities and likelihoods. Searches for approximate matches in large sets using a difference function are seen to be an open problem still, though several promising ideas have been suggested. Approximate matching (error correction) during parsing is briefly reviewed.
Automatic short answer grading (ASAG) is the task of assessing short natural language responses to objective questions using computational methods. The active research in this field has increased enormously of late with over 80 papers fitting a definition of ASAG. However, the past efforts have generally been ad-hoc and non-comparable until recently, hence the need for a unified view of the whole field. The goal of this paper is to address this aim with a comprehensive review of ASAG research and systems according to history and components. Our historical analysis identifies 35 ASAG systems within 5 temporal themes that mark advancement in methodology or evaluation. In contrast, our component analysis reviews 6 common dimensions from preprocessing to effectiveness. A key conclusion is that an era of evaluation is the newest trend in ASAG research, which is paving the way for the consolidation of the field.
Various known meta search engines are built for specific search results. Based on search query meta search engine returns an aggregate list of search results from number of search engines. In this article, significance of stop word elimination for better search results in meta search engine is discussed, and new model of meta search engine is proposed. The output by proposed meta search engine and existing meta search engine like dogpile; with stop words and without stop words; are compared. The result shows that retrieved links in new meta search engine, with and without stop words, is more than 90% same where as by existing meta search engine like dogpile differ with more than 90%.
Text sentiment analysis, also referred to as emotional polarity computation, has become a flourishing frontier in the text mining community. This paper studies online forums hotspot detection and forecast using sentiment analysis and text mining approaches. First, we create an algorithm to automatically analyze the emotional polarity of a text and to obtain a value for each piece of text. Second, this algorithm is combined with K-means clustering and support vector machine (SVM) to develop unsupervised text mining approach. We use the proposed text mining approach to group the forums into various clusters, with the center of each representing a hotspot forum within the current time span. The data sets used in our empirical studies are acquired and formatted from Sina sports forums, which spans a range of 31 different topic forums and 220,053 posts. Experimental results demonstrate that SVM forecasting achieves highly consistent results with K-means clustering. The top 10 hotspot forums listed by SVM forecasting resembles 80% of K-means clustering results. Both SVM and K-means achieve the same results for the top 4 hotspot forums of the year.
Students were observed directly, in a usability laboratory, and indirectly, by means of an extensive evaluation of responses, as they attempted interactive computer-marked assessment questions that required free-text responses of up to 20 words and as they amended their responses after receiving feedback. This provided more general insight into the way in which students actually engage with assessment and feedback, which is not necessarily the same as their self-reported behaviour. Response length and type varied with whether the question was in summative, purely formative, or diagnostic use, with the question itself, and most significantly with students’ interpretation of what the question author was looking for. Feedback was most effective when it was understood by the student, tailored to the mistakes that they had made and when it prompted students rather than giving the answer. On some occasions, students appeared to respond to the computer as if it was a human marker, supporting the ‘computers as social actors’ hypothesis, whilst on other occasions students seemed very aware that they were being marked by a machine.
Class-tested and coherent, this textbook teaches classical and web information retrieval, including web search and the related areas of text classification and text clustering from basic concepts. It gives an up-to-date treatment of all aspects of the design and implementation of systems for gathering, indexing, and searching documents; methods for evaluating systems; and an introduction to the use of machine learning methods on text collections. All the important ideas are explained using examples and figures, making it perfect for introductory courses in information retrieval for advanced undergraduates and graduate students in computer science. Based on feedback from extensive classroom experience, the book has been carefully structured in order to make teaching more natural and effective. Slides and additional exercises (with solutions for lecturers) are also available through the book's supporting website to help course instructors prepare their lectures.
SIMPLE: System Automatic Essay Assessment for Indonesian Language Subject Examination. Evaluation ofstudy of a student is a very important aspect of an educational process. Evaluation is aimed at measuring the level ofstudent understanding of the given lecture materials. Measuring student understanding of the course material, usingessay-type exam, is generally used as the evaluation tool. In this essay-type exam, the student has to answer questionsusing sentences, whereby choices of possible answers are not indicated. The student has to answer the questions withhis/her sentences. The answers may vary, since it reflects the student's best thoughts of the materials. One of theweaknesses of essay-type exam is the difficulty to grade the answers and it tends to be time consuming. Currently,automatic grading systems that may speed up the grading process, are being developed in many research institutions.The method used to grade, varies form one system to another, and one of the popular system is the Latent SemanticAnalysis (LSA). LSA is a method of grading essay by extracting words and representing the sentence in the form ofmathematical or statistical formulation, from a text with a relatively large number of words. The grade of the essay isdetermined, by matching the important words to a group of words prepared by the human rater. This paper describes aneffort to developed LSA, enhanced with word weighting, word order and the word synonym to improve the accuracy ofgrading. This system is called SIMPLE. SIMPLE is used to grade answers using bahasa Indonesia. The exam is carriedout on-line through the Web. From the experiments conducted, for small classes, the conformity of grade compared tothe grade of human rater lies between 69.80 % - 94.64 %, and for medium size classes the conformity lies between77.18 % - 98.42 % with the human rater. These results are roughly proportional with the result of LSA system, whichgrade essay given in English.Keywords: SIMPLE, latent semantic analysis, on-line examination, web
Contents 1 Introduction 1 2 A Purely Rule-based Stemmer for Bahasa Indonesia 3 2.1 Morphological Structure of Bahasa Indonesia Words . . . . . . . . . . . . . . . . . 3 2.2 The Porter Stemming Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.3 Porter Stemmer for Bahasa Indonesia . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.3.1 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 3 Evaluation of the Stemming Algorithm 11 3.1 Stemmer Quality Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.1.1 The Paice Evaluation Method . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.1.2 The Paice Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . 13 3.2 Error Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2.1 Inflectional Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2.2 Derivational Structure . . . . . . . . . . .
Short-answer e-assessment questions : five years on
- S Jordan
S. Jordan, "Short-answer e-assessment questions : five years on," Proc. 15th Int. Comput. Assist. Assess.
Conf., 2012.
Implementasi Cosine Similarity dan Algoritma Smith Waterman untuk Mendeteksi Kemiripan Teks
- V Imbar
- Radiant
- Adelia
- M Ayub
- A Dan Rehatta
Imbar, V., Radiant. Adelia, Ayub, M., dan Rehatta, A. 2014. Implementasi Cosine Similarity dan
Algoritma Smith Waterman untuk Mendeteksi Kemiripan Teks. Jurnal Informatika Volume 10, Nomor 1.
Perbandingan metode cosine similarity dan jaccard similarity untuk penilaian otomatis jawaban pendek
- U Hasanah
- D A Mutiara
U. Hasanah and D. A. Mutiara, "Perbandingan metode cosine similarity dan jaccard similarity untuk penilaian
otomatis jawaban pendek," Semin. Nas. Sist. Inf. dan Tek. Inform., no. 2019: SENSITIF 2019, pp. 1255-1263,
2019.
Wisdom of Students: A Consistent Automatic Short Answer Grading Technique
- S Roy
- S Dandapat
- A Nagesh
S. Roy, S. Dandapat, A. Nagesh, and N. Y., "Wisdom of Students: A Consistent Automatic Short Answer
Grading Technique," Proc. 13th Int. Conf. Nat. Lang. Process., pp. 178-187, 2016.
Grading Essays by Computer: Progress Report
- E B Page
E. B. Page, "Grading Essays by Computer: Progress Report," Invit. Conf. Test. Probl. 29 October, 1966, vol. 47,
no. 5, pp. 87-100, 1966.
Rancang Bangun Search Engine Tafsir Al-Quran Yang Mampu Memproses Teks Bahasa Indonesia Menggunakan Metode Jaccard Similarity, Fakultas Sains dan Teknologi Universitas Islam Negeri Maulana Malik Ibrahim Malang
- S Purwandari
S. Purwandari, Rancang Bangun Search Engine Tafsir Al-Quran Yang Mampu Memproses Teks Bahasa
Indonesia Menggunakan Metode Jaccard Similarity, Fakultas Sains dan Teknologi Universitas Islam Negeri
Maulana Malik Ibrahim Malang, 2012, pp. 9-27.
Introduction of Information Retrieval
- C D Manning
- P Raghavan
- H Mschutze
Manning, C. D., Raghavan, P., & mSchutze, H. (2009). Introduction of Information Retrieval, Cambridge
University Press.
Document Retrieval for Question Answering : A Quantitative Evaluation of Text Preprocessing
- G Carvalho
- D M De Matos
- V Rocio
G. Carvalho, D. M. de Matos, and V. Rocio, "Document Retrieval for Question Answering : A
Quantitative Evaluation of Text Preprocessing," Proc. ACM first Ph. D. Work. CIKM, pp. 125-130, 2007.
- J Fleiss
- B Levin
- Cho Paik
Fleiss J, Levin B, Cho Paik M. Statistical Methods for Rates and Proportions. Third Edit.
Technometrics. 2004; 46: 263-264.