Semantic Similarity Approach Research Articles

Toward a recommender system for assisting customers at risk of churning in e-commerce platforms based on a combination of Social Network Analysis (SNA) and deep learning

Recently, e-commerce platforms have gained significant attention in the media. As the number of customers using these platforms continues to grow, they face challenges such as limited support, making it increasingly difficult for customers to find answers to their inquiries, leading to a high attrition rate. This study aims to address the issue of unanswered customer queries in online product discussion forums by leveraging a combination of SNA and deep learning techniques. The primary objective is to reduce the attrition rate by enhancing customer support through peer-to-peer interactions. Initially, we analyze the customer interaction network and thread structures using SNA to identify isolated inquiries. Following this, we apply a deep learning-based model to calculate a similarity score between these queries, which serves as the foundation for our semantic similarity approach to product discussion questions. The results of our experiment, conducted on a Moroccan e-commerce platform, demonstrate the efficacy of our recommendation method in connecting customers with relevant answers and fellow customers who can assist them. The proposed deep learning model provided an accuracy of 0.8529 and a mean squared error of 0.1168.

Aspect-Based Sentiment Analysis for Financial Review with Implicit Aspect and Opinion Using Semantic Similarity and Hybrid Approach

Aspect-Based Sentiment Analysis for Financial Review with Implicit Aspect and Opinion Using Semantic Similarity and Hybrid Approach

Browsing target extraction and spatiotemporal preference mining from the complex virtual trajectories

Public Map Service Platforms (PMSPs) aggregate and disseminate the earth observation data. Leveraging spatiotemporal preference patterns derived from browsing targets within complex virtual trajectories on PMSPs aids in constructing user-profiles and comprehending their intentions. However, complex virtual trajectories, characterized by numerous trajectory points and overlapping pyramidal spatial structures, introduce inefficiencies and inaccuracies during browsing target extraction. To mitigate this, we propose an Optimized Spatial Structure Segmentation (OSSS) method that divides complex virtual trajectories into sub-trajectories with simplified spatial structures, enhancing the efficiency of browsing target extraction. Spatiotemporal reconstruction of these sub-trajectories establishes sequences of browsing targets, revealing patterns of interest transitions. Moreover, recognizing the spatial uncertainty inherent in complex virtual trajectories, which results in imprecise matching between browsing targets and spatial features, we introduce a spatial co-occurrence semantic modeling approach. This involves constructing a POI semantic space and introducing a semantic similarity matching method to reduce spatial uncertainty and refine the accuracy of mining spatiotemporal preference patterns. We evaluate these methods using real-world data from Tianditu. Results demonstrate that the OSSS improves extraction efficiency by 3.45 times and accuracy by 18.84%. Additionally, the semantic similarity approach combined with spatial co-occurrence effectively mitigates spatial uncertainty. This research contributes to advancing the intelligence of PMSPs.

Neurofuzzy semantic similarity measurement

Automatically identifying the degree of semantic similarity between two small pieces of text has grown in importance recently. Its impact on various computer-related domains and recent breakthroughs in neural computation has increased the opportunities for better solutions to be developed. This work contributes a neurofuzzy approach for semantic textual similarity that uses neural networks and fuzzy logics. The idea is to combine the capabilities of the deep neural models for working with text with the ones from fuzzy logic for aggregating numerical data. The results of our experiments suggest that such an approach can accurately determine semantic similarity.

Mapping the Landscape of Blockchain Technology Knowledge: A Patent Co-Citation and Semantic Similarity Approach

The potential applications of blockchain technology across various business functions and industries have generated significant interest. However, its underlying knowledge structure remains unclear. This study aimed to gain a deeper understanding of the technological domain and knowledge structure of blockchain technology by analyzing 4753 USPTO patent data from 2008 to 2019. We used multiple approaches, such as analyzing patent filing volumes, constructing co-citation networks, and examining text (patent abstract) data with a variant of bidirectional encoder representations from transformers (BERT). The results demonstrate the advantages of using an NLP-based BERT text analysis approach for examining technological knowledge and relationships within the blockchain technology field. Our findings reveal that the field of blockchain technology is expanding and diversifying, with increasing patent filings in both cryptocurrency and distributed ledger technologies and growing knowledge similarity between these two subdomains. We also found that patent assignees (companies) engage differently in innovative activities within the blockchain technology domain based on their prior experience in the field. These results hold potential for informing future research in emerging technology studies and guiding industry and policy decisions related to blockchain technology.

A Semantics-Based Clustering Approach for Online Laboratories Using K-Means and HAC Algorithms

Due to the availability of a vast amount of unstructured data in various forms (e.g., the web, social networks, etc.), the clustering of text documents has become increasingly important. Traditional clustering algorithms have not been able to solve this problem because the semantic relationships between words could not accurately represent the meaning of the documents. Thus, semantic document clustering has been extensively utilized to enhance the quality of text clustering. This method is called unsupervised learning and it involves grouping documents based on their meaning, not on common keywords. This paper introduces a new method that groups documents from online laboratory repositories based on the semantic similarity approach. In this work, the dataset is collected first by crawling the short real-time descriptions of the online laboratories’ repositories from the Web. A vector space is created using frequency-inverse document frequency (TF-IDF) and clustering is done using the K-Means and Hierarchical Agglomerative Clustering (HAC) algorithms with different linkages. Three scenarios are considered: without preprocessing (WoPP); preprocessing with steaming (PPwS); and preprocessing without steaming (PPWoS). Several metrics have been used for evaluating experiments: Silhouette average, purity, V-measure, F1-measure, accuracy score, homogeneity score, completeness and NMI score (consisting of five datasets: online labs, 20 NewsGroups, Txt_sentoken, NLTK_Brown and NLTK_Reuters). Finally, by creating an interactive webpage, the results of the proposed work are contrasted and visualized.

Automatic Arabic Grading System for Short Answer Questions

The era of technology and digitalization has been advantageous to the educational sector. The examination system is one of the most important educational pillars that have been affected. As automatic exam grading is a revolution in the history of exam development, and therefore the automatic grading system has started to replace the traditional assessment system. The automatic grading system allows the examiners to automatically assign grades for students” answers compared to the model answers. And, generate results based on the examiners’ answers. In this paper, we especially address the short answer questions. Most research has been done on the English language. On the other side, few research works have been conducted on Arabic. Moreover, Arabic is considered one of the rare resource languages. This paper is aimed to build an Automatic Arabic Short Answer Grading (AASAG) model using semantic similarity approaches. It is used to measure the semantic similarity between the student and model answer. The proposed model is applied to one of the Arabic scarce publicly available datasets which is called (AR-ASAG). It contains 2133 pairs of models and student answers in several versions such as txt, xml, and db. The efficiency of the proposed model was evaluated through two conducted experiments using two weighting schemas local, and hybrid local and global weighting schema. The developed approach with hybrid local and global weight-based LSA achieved better results than using local weight-based LSA with (82.82%) as F1-score value, and 0.798 as an RMSE (Root-Mean-Square Error) value using hybrid local and global weight-based LSA.

Hybrid Method for Semantic Similarity Computation Using Weighted Components in Ontology

In this paper, the researchers propose an approach to measure the semantic similarity between two concepts in an ontology like WordNet and DBpedia. Some earlier semantic similarity approaches proposed concentrated on the ontology structure between concepts and some concentrated only on the information content of concepts. This paper proposes a semantic similarity approach with path length, information content, and semantic depth (i.e., PLICD) to combine both path length as well as information content-based approaches. This proposed approach uses weighted shortest path length and information content calculated using semantic depth and hyponyms of the concepts to measure semantic similarity between two concepts. Through experimentations performed on WordNet and DBpedia, the researchers note that the PLICD semantic similarity approach has delivered a statistically meaningful enhancement as compared to the other semantic similarity approaches concerning accuracy and F score.

Text-based experiment retrieval in genomic databases

With the growing number of genomic data in public repositories, efficient search methodologies have become a basic need to reach the relevant genomic data. However, this need cannot be fulfilled with the current repositories because they offer a limited search option which is a lexical matching of textual descriptions or metadata of the experiments. This technique is insufficient to get the required information needed to detect similarities between experiments within a large data collection. Due to the limitation of the existing repositories, in this study, we develop a text-based experiment retrieval framework by using both lexical and semantic similarity approaches to find similarities between experiments, and their retrieval performance was compared. This study is the first attempt to use text-driven semantic analysis approaches for developing a retrieval framework for experiments. An empirical study was conducted on a large textual description of Arabidopsis microarray experiments from the Gene Expression Omnibus database. In the proposed model, Jaccard similarity was used as a lexical similarity approach; Latent Semantic Analysis, Probabilistic Latent Semantic Analysis and Latent Dirichlet allocation were used as semantic similarity approaches to detect similarities between the textual descriptions of the experiments. According to the experimental results, relevant experiments can be retrieved successfully by text-driven semantic similarity approaches compared with the lexical similarity approach.

A formula embedding approach for semantic similarity and relatedness between formulas

SummaryThe mathematical formula is one of the most vital components in a scientific document, which can explicitly describe various complex concepts and ideas. In addition to numerical calculations, they are also used to clarify definitions and disambiguate explanations transcribed in natural language. Nevertheless, the formulas have a noteworthy impact in the scientific documents, the existing information retrieval systems have limited access to scientific documents based on formulas‐based queries. To accomplish this, in this research, we have studied and implemented the formula embedding approach, which encodes the formula into the embedded vector. For encoding the formula, we have used pretrained sentence bidirectional encoder representations from transformers model. The proposed embedding model takes the latex formula as input and generates an upshot as a fixed dimensional embedding representation. In addition to this, the Siamese network is used to reform the semantic meaning of the formulas. Furthermore, the embedding of the formulas and the queried formula are compared, and cosine similarity is estimated. The performance of the suggested methodology is verified using a math stack exchange corpus of ARQMath 2020, and obtained results have shown a remarkable contribution in the task of formula retrieval.

NGram Approach for Semantic Similarity on Arabic Short Text

Measuring the semantic similarity between words requires a method that can simulate human thought. The use of computers to quantify and compare semantic similarities has become an important research area in various fields, including artificial intelligence, knowledge management, information re-trieval, and natural language processing. Computational seman-tics require efficient measures for computing concept similarity, which still need to be developed. Several computational measures quantify semantic similarity based on knowledge resources such as the WordNet taxonomy. Several measures based on taxonom-ical parameters have been applied to optimize the expression for content semantics. This paper presents a new similarity measure for quantifying the semantic similarity between concepts, words, sentences, short text, and long text based on NGram features and Synonyms of NGram related to the same domain. The proposed algorithm was tested on 700 tweets, and the semantic similarity values were compared with cosine similarity on the same dataset. The results were analyzed manually by a domain expert who concluded that the values provided by the proposed algorithm were better than the cosine similarity values within the selected domain regarding the semantic similarity between the datasets’ short texts.

Cross-lingual Text Reuse Detection Using Translation Plus Monolingual Analysis for English-Urdu Language Pair

Cross-Lingual Text Reuse Detection (CLTRD) has recently attracted the attention of the research community due to a large amount of digital text readily available for reuse in multiple languages through online digital repositories. In addition, efficient machine translation systems are freely and readily available to translate text from one language into another, which makes it quite easy to reuse text across languages, and consequently difficult to detect it. In the literature, the most prominent and widely used approach for CLTRD is Translation plus Monolingual Analysis (T+MA). To detect CLTR for English-Urdu language pair, T+MA has been used with lexical approaches, namely, N-gram Overlap, Longest Common Subsequence, and Greedy String Tiling. This clearly shows that T+MA has not been thoroughly explored for the English-Urdu language pair. To fulfill this gap, this study presents an in-depth and detailed comparison of 26 approaches that are based on T+MA. These approaches include semantic similarity approaches (semantic tagger based approaches, WordNet-based approaches), probabilistic approach (Kullback-Leibler distance approach), monolingual word embedding-based approaches siamese recurrent architecture, and monolingual sentence transformer-based approaches for English-Urdu language pair. The evaluation was carried out using the CLEU benchmark corpus, both for the binary and the ternary classification tasks. Our extensive experimentation shows that our proposed approach that is a combination of 26 approaches obtained an F 1 score of 0.77 and 0.61 for the binary and ternary classification tasks, respectively, and outperformed the previously reported approaches [ 41 ] ( F 1 = 0.73) for the binary and ( F 1 = 0.55) for the ternary classification tasks) on the CLEU corpus.

Network-driven analysis of human\u2013Plasmodium falciparum interactome: processes for malaria drug discovery and extracting in silico targets

BackgroundThe emergence and spread of malaria drug resistance have resulted in the need to understand disease mechanisms and importantly identify essential targets and potential drug candidates. Malaria infection involves the complex interaction between the host and pathogen, thus, functional interactions between human and Plasmodium falciparum is essential to obtain a holistic view of the genetic architecture of malaria. Several functional interaction studies have extended the understanding of malaria disease and integrating such datasets would provide further insights towards understanding drug resistance and/or genetic resistance/susceptibility, disease pathogenesis, and drug discovery.MethodsThis study curated and analysed data including pathogen and host selective genes, host and pathogen protein sequence data, protein–protein interaction datasets, and drug data from literature and databases to perform human-host and P. falciparum network-based analysis. An integrative computational framework is presented that was developed and found to be reasonably accurate based on various evaluations, applications, and experimental evidence of outputs produced, from data-driven analysis.ResultsThis approach revealed 8 hub protein targets essential for parasite and human host-directed malaria drug therapy. In a semantic similarity approach, 26 potential repurposable drugs involved in regulating host immune response to inflammatory-driven disorders and/or inhibiting residual malaria infection that can be appropriated for malaria treatment. Further analysis of host–pathogen network shortest paths enabled the prediction of immune-related biological processes and pathways subverted by P. falciparum to increase its within-host survival.ConclusionsHost–pathogen network analysis reveals potential drug targets and biological processes and pathways subverted by P. falciparum to enhance its within malaria host survival. The results presented have implications for drug discovery and will inform experimental studies.

Multi-faceted semantic clustering with text-derived phenotypes

Identification of ontology concepts in clinical narrative text enables the creation of phenotype profiles that can be associated with clinical entities, such as patients or drugs. Constructing patient phenotype profiles using formal ontologies enables their analysis via semantic similarity, in turn enabling the use of background knowledge in clustering or classification analyses. However, traditional semantic similarity approaches collapse complex relationships between patient phenotypes into a unitary similarity scores for each pair of patients. Moreover, single scores may be based only on matching terms with the greatest information content (IC), ignoring other dimensions of patient similarity. This process necessarily leads to a loss of information in the resulting representation of patient similarity, and is especially apparent when using very large text-derived and highly multi-morbid phenotype profiles. Moreover, it renders finding a biological explanation for similarity very difficult; the black box problem. In this article, we explore the generation of multiple semantic similarity scores for patients based on different facets of their phenotypic manifestation, which we define through different sub-graphs in the Human Phenotype Ontology. We further present a new methodology for deriving sets of qualitative class descriptions for groups of entities described by ontology terms. Leveraging this strategy to obtain meaningful explanations for our semantic clusters alongside other evaluation techniques, we show that semantic clustering with ontology-derived facets enables the representation, and thus identification of, clinically relevant phenotype relationships not easily recoverable using overall clustering alone. In this way, we demonstrate the potential of faceted semantic clustering for gaining a deeper and more nuanced understanding of text-derived patient phenotypes.

Assessing Lexical Psychological Properties in Second Language Production: A Dynamic Semantic Similarity Approach.

Previous studies of the lexical psycholinguistic properties (LPPs) in second language (L2) production have assessed the degree of an LPP dimension of an L2 corpus by computing the mean ratings of unique content words in the corpus for that dimension, without considering the possibility that learners at different proficiency levels may perceive the degree of that dimension of the same words differently. This study extended a dynamic semantic similarity algorithm to estimate the degree of five different LPP dimensions of several sub-corpora of the Education First-Cambridge Open Language Database representing L2 English learners at different proficiency levels. Our findings provide initial evidence for the validity of the algorithm for assessing the LPPs in L2 production and contribute useful insights into between-proficiency relationships and cross-proficiency differences in the LPPs in L2 production as well as the relationships among different LPP dimensions.

Automated Short-Answer Grading using Semantic Similarity based on Word Embedding

Automatic short-answer grading (ASAG) is a system that aims to help speed up the assessment process without an instructor’s intervention. Previous research had successfully built an ASAG system whose performance had a correlation of 0.66 and mean absolute error (MAE) starting from 0.94 with a conventionally graded set. However, this study had a weakness in the need for more than one reference answer for each question. It used a string-based equation method and keyword matching process to measure the sentences’ similarity in order to produce an assessment rubric. Thus, our study aimed to build a more concise short-answer automatic scoring system using a single reference answer. The mechanism used a semantic similarity measurement approach through word embedding techniques and syntactic analysis to assess the learner’s accuracy. Based on the experiment results, the semantic similarity approach showed a correlation value of 0.70 and an MAE of 0.70 when compared with the grading reference.

Arabic Semantic Similarity Approach for Farmers’ Complaints

Semantic similarity is applied for many areas in Natural Language Processing, such as information retrieval, text classification, plagiarism detection, and others. Many researchers used semantic similarity for English texts, but few used for Arabic due to the ambiguity of Arabic concepts in both sense and morphology. Therefore, the first contribution in this paper is developing a semantic similarity approach between Arabic sentences. Nowadays, the world faces a global problem of coronavirus disease. In light of these circumstances and distancing's imposition, it is difficult for farmers to physically communicate with agricultural experts to provide advice and find suitable solutions for their agricultural complaints. In addition, traditional practices still are used by most farmers. Thus, our second contribution is helping the farmers solve their Arabic agricultural complaints using our proposed approach. The Latent Semantic Analysis approach is applied to retrieve the most problem-related semantic to a farmer's complaint and find the related solution for the farmer. Two methods are used in this approach as a weighting schema for data representation are Term Frequency and Term Frequency-Inverse Document Frequency. The proposed model has also classified the big agricultural dataset and the submitted farmer complaint according to the crop type using MapReduce Support Vector Machine to improve the performance of semantic similarity results. The proposed approach's performance with Term Frequency-Inverse Document Frequency-based Latent Semantic Analysis achieved better than its counterparts with an F-measure of 86.7%.

Intelligent recognition of semantic relationships based on antonymy

Since computing semantic similarity tends to simulate the thinking process of humans, semantic dissimilarity must play a part in this process. In this paper, we present a new approach for semantic similarity measuring by taking consideration of dissimilarity into the process of computation. Specifically, the proposed measures explore the potential antonymy in the hierarchical structure of WordNet to represent the dissimilarity between concepts and then combine the dissimilarity with the results of existing methods to achieve semantic similarity results. The relation between parameters and the correlation value is discussed in detail. The proposed model is then applied to different text granularity levels to validate the correctness on similarity measurement. Experimental results show that the proposed approach not only achieves high correlation value against human ratings but also has effective improvement to existing path-distance based methods on the word similarity level, in the meanwhile effectively correct existing sentence similarity method in some cases in Microsoft Research Paraphrase Corpus and SemEval-2014 date set.

Developing MCQA Framework for Basic Science Subjects using Distributed Similarity Model and Classification Based Approaches

In this paper, we proposed a novel approach to improve the performance of multiple choice question answering (MCQA) system using distributed semantic similarity and classification approach. We mainly focus on science-based MCQ which is really difficult to handle. Our proposed method is based on the hypothesis that the relation between question and answer of that question will be high in distributional semantic model rather than other options of that question. We are using IJCNLP shared Task 5 and SciQ dataset for our experiments. We have built three Models (i.e., Model 1, Model 2, Model 3) based on the dataset format. The basic difference between IJCNLP Task 5 and SciQ datasets is that SciQ dataset contains supporting text with questions whereas IJCNLP Task 5 dataset does not contain supporting text. Model 1 and Model 2 are mainly built to deal with IJCNLP Task 5 dataset whereas Model 3 is mainly built for SciQ dataset. Model 2 is mainly built to deal with the dependencies between options (i.e., all of these, two of them, none of them) whereas Model 1 is the basic model for MCQA and it cannot capture the dependencies between options. We also compare the result of SciQ dataset with supporting text (i.e., using Model 3) and without supporting text (i.e., using Model 1). We also compared our system with other existing methods. Though in some cases the performance of our proposed method is not satisfactory, we have noted that our submission is simple and robust that allows it to be more easily integrated into complex applications. This work investigates different techniques for choosing the correct answer of a given question in MCQA system. These experiments may therefore be useful to improve the performance of current science-based question answering (QA) systems. For IJCNLP Task 5 dataset, we achieved 44.5% using Model 2 and PubMed Dataset. Similarly for SciQ dataset we achieved 82.25% using Model 3 and PubMed dataset.

Semantic Similarity Analysis Reveals Robust Gene-Disease Relationships in Developmental and Epileptic Encephalopathies

SummaryMore than 100 genetic etiologies have been identified in developmental and epileptic encephalopathies (DEEs), but correlating genetic findings with clinical features at scale has remained a hurdle because of a lack of frameworks for analyzing heterogenous clinical data. Here, we analyzed 31,742 Human Phenotype Ontology (HPO) terms in 846 individuals with existing whole-exome trio data and assessed associated clinical features and phenotypic relatedness by using HPO-based semantic similarity analysis for individuals with de novo variants in the same gene. Gene-specific phenotypic signatures included associations of SCN1A with “complex febrile seizures” (HP: 0011172; p = 2.1 × 10−5) and “focal clonic seizures” (HP: 0002266; p = 8.9 × 10−6), STXBP1 with “absent speech” (HP: 0001344; p = 1.3 × 10−11), and SLC6A1 with “EEG with generalized slow activity” (HP: 0010845; p = 0.018). Of 41 genes with de novo variants in two or more individuals, 11 genes showed significant phenotypic similarity, including SCN1A (n = 16, p < 0.0001), STXBP1 (n = 14, p = 0.0021), and KCNB1 (n = 6, p = 0.011). Including genetic and phenotypic data of control subjects increased phenotypic similarity for all genetic etiologies, whereas the probability of observing de novo variants decreased, emphasizing the conceptual differences between semantic similarity analysis and approaches based on the expected number of de novo events. We demonstrate that HPO-based phenotype analysis captures unique profiles for distinct genetic etiologies, reflecting the breadth of the phenotypic spectrum in genetic epilepsies. Semantic similarity can be used to generate statistical evidence for disease causation analogous to the traditional approach of primarily defining disease entities through similar clinical features.