Library Recommendation Research Articles

Neural Library Recommendation by Embedding Project-Library Knowledge Graph

Neural Library Recommendation by Embedding Project-Library Knowledge Graph

Task-Oriented ML/DL Library Recommendation Based on a Knowledge Graph

AI applications often use ML/DL (Machine Learning/Deep Learning) models to implement specific AI tasks. As application developers usually are not AI experts, they often choose to integrate existing implementations of ML/DL models as libraries for their AI tasks. As an active research area, AI attracts many researchers and produces a lot of papers every year. Many of the papers propose ML/DL models for specific tasks and provide their implementations. However, it is not easy for developers to find ML/DL libraries that are suitable for their tasks. The challenges lie in not only the fast development of AI application domains and techniques, but also the lack of detailed information of the libraries such as environmental dependencies and supporting resources. In this paper, we conduct an empirical study on ML/DL library seeking questions on Stack Overflow to understand the developers' requirements for ML/DL libraries. Based on the findings of the study, we propose a task-oriented ML/DL library recommendation approach, called MLTaskKG. It constructs a knowledge graph that captures AI tasks, ML/DL models, model implementations, repositories, and their relationships by extracting knowledge from different sources such as ML/DL resource websites, papers, ML/DL frameworks, and repositories. Based on the knowledge graph, MLTaskKG recommends ML/DL libraries for developers by matching their requirements on tasks, model characteristics, and implementation information. Our evaluation shows that 92.8% of the tuples sampled from the resulting knowledge graph are correct, demonstrating the high quality of the knowledge graph. A further experiment shows that MLTaskKG can help developers find suitable ML/DL libraries using 47.6% shorter time and with 68.4% higher satisfaction.

Neighbor Library-Aware Graph Neural Network for Third Party Library Recommendation

Modern software development has moved toward agile growth and rapid delivery, where developers must meet the changing needs of users instantaneously. In such a situation, plug-and-play Third-Party Libraries (TPLs) introduce a considerable amount of convenience to developers. However, selecting the exact candidate that meets the project requirements from the countless TPLs is challenging for developers. Previous works have considered setting up a personalized recommender system to suggest TPLs for developers. Unfortunately, these approaches rarely consider the complex relationships between applications and TPLs, and are unsatisfactory in accuracy, training speed, and convergence speed. In this paper, we propose a new end-to-end recommendation model called Neighbor Library-Aware Graph Neural Network (NLA-GNN). Unlike previous works, we only initialize one type of node embedding, and construct and update all types of node representations using Graph Neural Networks (GNN). We use a simplified graph convolution operation to alternate the information propagation process to increase the training efficiency and eliminate the heterogeneity of the app-library bipartite graph, thus efficiently modeling the complex high-order relationships between the app and the library. Extensive experiments on large-scale real-world datasets demonstrate that NLA-GNN achieves consistent and remarkable improvements over state-of-the-art baselines for TPL recommendation tasks.

KG2Lib: knowledge-graph-based convolutional network for third-party library recommendation

KG2Lib: knowledge-graph-based convolutional network for third-party library recommendation

Fast Library Recommendation in Software Dependency Graphs with Symmetric Partially Absorbing Random Walks

To help developers discover libraries suited to their software projects, automated approaches often start from already employed libraries and recommend more based on co-occurrence patterns in other projects. The most accurate project–library recommendation systems employ Graph Neural Networks (GNNs) that learn latent node representations for link prediction. However, GNNs need to be retrained when dependency graphs are updated, for example, to recommend libraries for new projects, and are thus unwieldy for scalable deployment. To avoid retraining, we propose that recommendations can instead be performed with graph filters; by analyzing dependency graph dynamics emulating human-driven library discovery, we identify low-pass filtering with memory as a promising direction and introduce a novel filter, called symmetric partially absorbing random walks, which infers rather than trains the parameters of filters with node-specific memory to guarantee low-pass filtering. Experiments on a dependency graph between Android projects and third-party libraries show that our approach makes recommendations with a quality and diversification loosely comparable to those state-of-the-art GNNs without computationally intensive retraining for new predictions.

A Markov logic network method for reconstructing association rule-mining tasks in library book recommendation

PurposeThis study aims to overcome the problem of traditional association rules relying almost entirely on expert experience to set relevant interest indexes in mining. Second, this project can effectively solve the problem of four types of rules being present in the database at the same time. The traditional association algorithm can only mine one or two types of rules and cannot fully explore the database knowledge in the decision-making process for library recommendation.Design/methodology/approachThe authors proposed a Markov logic network method to reconstruct association rule-mining tasks for library recommendation and compared the method proposed in this paper to traditional Apriori, FP-Growth, Inverse, Sporadic and UserBasedCF algorithms on two history library data sets and the Chess and Accident data sets.FindingsThe method used in this project had two major advantages. First, the authors were able to mine four types of rules in an integrated manner without having to set interest measures. In addition, because it represents the relevance of mining in the network, decision-makers can use network visualization tools to fully understand the results of mining in library recommendation and data sets from other fields.Research limitations/implicationsThe time cost of the project is still high for large data sets. The authors will solve this problem by mapping books, items, or attributes to higher granularity to reduce the computational complexity in the future.Originality/valueThe authors believed that knowledge of complex real-world problems can be well captured from a network perspective. This study can help researchers to avoid setting interest metrics and to comprehensively extract frequent, rare, positive, and negative rules in an integrated manner.

Personalized recommendation by using fused user preference to construct smart library

In online digital library, it makes people be convenient to visit latest books or magazines via digitization. Online digital library becomes the platform for people to search and browse latest books or magazines. From digital library to smart library, the key is how to recommend interesting items from personalized preference according to visiting history records, comments, and discussions. This paper introduces user preference into digital library recommendation system. Generally, if two users have similar preference, they also like the books or magazines from the same or related topics. First, the topics is estimated by a Latent Dirichlet Allocation (LDA) model; second, the topics with high user preference score is recommended to the user. Thus, the user can receive the item list which are close to the topics which he or she is interested in. The experimental results on a university digital library show the effectiveness of the user preference based recommendation system for smart library.

A hybrid recommender system for patron driven library acquisition and weeding

Nowadays the explosion of information sources has shaped how library users access information and provide feedback on their preferences. Therefore, faced with this explosion and the blossoming of digital libraries, modern libraries must take up the challenge of meeting the needs of their users and considering their opinions and preferences in order to offer them adequate resources and henceforth eliminate those that are unsatisfactory.Almost all library recommender systems aim to provide users with items of interest to them. However, despite its definite interest, the staff-oriented adaptation and application of this revolutionary technique to the collection development process is still in an embryonic stage.We propose a patron-driven hybrid library recommender system that uses machine learning techniques to recommend and assist in the acquisition and weeding decision-making operations by extracting and analyzing users’ opinions and ratings. The recommender system is applied and validated in a real national library case using Amazon’s digital library and the library’s catalog as a data source.

Research on Library Personalized Recommendation System Based on Restricted Boltzmann Machine

At present, most recommendation systems in libraries are content-based and collaborative filtering-based, but these recommendation systems ignore the deep-seated characteristics of readers' personalized information. In order to improve the function of Library recommendation system, this paper proposes a library recommendation system based on restricted Boltzmann machine and collaborative filtering algorithm, and simulates the performance of the algorithm. The results show that the proposed algorithm has good application effect.

Effects of case library recommendation system on problem solving and knowledge structure development

Case-based reasoning posits that learners can use their prior experience to solve new problems. This theory is cited to explain the benefits of problem-based learning (PBL), especially as it relates to knowledge structure development. However, critics argue that learners lack the relevant knowledge structures to simultaneously learn new content and solve complex problems. In terms of learning design, theorists suggest a set of cases (case library) can be used as vicarious memory and thus bridge the experience gap. While this may be beneficial in theory, studies show experts and novices tend to process the details of a case in markedly different ways, which would be problematic in terms of case libraries' ability to scaffolding problem-solving. To address this challenge, this study compared the following conditions in terms of argumentation and knowledge structure development: PBL only, PBL with static case library, PBL with recommendation system case library. Both the case library conditions outperformed the PBL-only condition in terms of initial argument development. However, the PBL with recommendation system case library outperformed the other conditions on rebuttal development. Implications for PBL, CBR, knowledge structure development, and learning design are discussed.

Knowledge Graph Enhanced Third-Party Library Recommendation for Mobile Application Development

With the prevalence of smart terminal devices and the rapid development of the mobile Internet, mobile application markets become increasingly prosperous. Third-party libraries have played an essential role in mobile application development. These libraries can shorten development time, increase development efficiency, and improve development quality. Currently, a large number of third-party libraries have been published, which puts a heavy burden on developers in selecting appropriate libraries. Towards this issue, in this paper, we propose a novel third-party library recommendation approach by integrating topic modeling and knowledge graph techniques. In the topic modeling component, we extract topics from textual application descriptions and make recommendations based on libraries used by applications that share similar topics with the new application to develop. In the knowledge graph component, we leverage knowledge graph to incorporate structured information of third-party libraries and applications, as well as the interaction information of applications and libraries for the recommendation. Experiments conducted on a real-world dataset show that our proposed approach outperforms several state-of-the-art approaches in terms of recommendation performance.

Why reinventing the wheels? An empirical study on library reuse and re-implementation

Nowadays, with the rapid growth of open source software (OSS), library reuse becomes more and more popular since a large amount of third- party libraries are available to download and reuse. A deeper understanding on why developers reuse a library (i.e., replacing self-implemented code with an external library) or re-implement a library (i.e., replacing an imported external library with self-implemented code) could help researchers better understand the factors that developers are concerned with when reusing code. This understanding can then be used to improve existing libraries and API recommendation tools for researchers and practitioners by using the developers concerns identified in this study as design criteria. In this work, we investigated the reasons behind library reuse and re-implementation. To achieve this goal, we first crawled data from two popular sources, F-Droid and GitHub. Then, potential instances of library reuse and re-implementation were found automatically based on certain heuristics. Next, for each instance, we further manually identified whether it is valid or not. For library re-implementation, we obtained 82 instances which are distributed in 75 repositories. We then conducted two types of surveys (i.e., individual survey to corresponding developers of the validated instances and another open survey) for library reuse and re-implementation. For library reuse individual survey, we received 36 responses out of 139 contacted developers. For re-implementation individual survey, we received 13 responses out of 71 contacted developers. In addition, we received 56 responses from the open survey. Finally, we perform qualitative and quantitative analysis on the survey responses and commit logs of the validated instances. The results suggest that library reuse occurs mainly because developers were initially unaware of the library or the library had not been introduced. Re-implementation occurs mainly because the used library method is only a small part of the library, the library dependencies are too complicated, or the library method is deprecated. Finally, based on all findings obtained from analyzing the surveys and commit messages, we provided a few suggestions to improve the current library recommendation systems: tailored recommendation according to users’ preferences, detection of external code that is similar to a part of the users’ code (to avoid duplication or re-implementation), grouping similar recommendations for developers to compare and select the one they prefer, and disrecommendation of poor-quality libraries.

Accurate Library Recommendation Using Combining Collaborative Filtering and Topic Model for Mobile Development

Accurate Library Recommendation Using Combining Collaborative Filtering and Topic Model for Mobile Development

Designing Punjabi Poetry Classifiers Using Machine Learning and Different Textual Features

Analysis of poetic text is very challenging from computational linguistic perspective. Computational analysis of literary arts, especially poetry, is very difficult task for classification. For library recommendation system, poetries can be classified on various metrics such as poet, time period, sentiments and subject matter. In this work, content-based Punjabi poetry classifier was developed using Weka toolset. Four different categories were manually populated with 2034 poems Nature and Festival (NAFE), Linguistic and Patriotic (LIPA), Relation and Romantic (RORE), Philosophy and Spiritual (PHSP) categories consists of 505, 399, 529 and 601 numbers of poetries, respectively. These poetries were passed to various pre-processing sub phases such as tokenization, noise removal, stop word removal, and special symbol removal. 31938 extracted tokens were weighted using Term Frequency (TF) and Term Frequency-Inverse Document Frequency (TF-IDF) weighting scheme. Based upon poetry elements, three different textual features (lexical, syntactic and semantic) were experimented to develop classifier using different machine learning algorithms. Naive Bayes (NB), Support Vector Machine, Hyper pipes and K-nearest neighbour algorithms were experimented with textual features. The results revealed that semantic feature performed better as compared to lexical and syntactic. The best performing algorithm is SVM and highest accuracy (76.02%) is achieved by incorporating semantic information associated with words.

A Big Data smart library recommender system for an educational institution

PurposeWith the exponential growth of the amount of data, the most sophisticated systems of traditional libraries are not able to fulfill the demands of modern business and user needs. The purpose of this paper is to present the possibility of creating a Big Data smart library as an integral and enhanced part of the educational system that will improve user service and increase motivation in the continuous learning process through content-aware recommendations.Design/methodology/approachThis paper presents an approach to the design of a Big Data system for collecting, analyzing, processing and visualizing data from different sources to a smart library specifically suitable for application in educational institutions.FindingsAs an integrated recommender system of the educational institution, the practical application of Big Data smart library meets the user needs and assists in finding personalized content from several sources, resulting in economic benefits for the institution and user long-term satisfaction.Social implicationsThe need for continuous education alters business processes in libraries with requirements to adopt new technologies, business demands, and interactions with users. To be able to engage in a new era of business in the Big Data environment, librarians need to modernize their infrastructure for data collection, data analysis, and data visualization.Originality/valueA unique value of this paper is its perspective of the implementation of a Big Data solution for smart libraries as a part of a continuous learning process, with the aim to improve the results of library operations by integrating traditional systems with Big Data technology. The paper presents a Big Data smart library system that has the potential to create new values and data-driven decisions by incorporating multiple sources of differential data.

Research on Library Recommendation Reading Service System Based on Adaptive Algorithm

In order to facilitate the user recommendation service system of library access, predict the future number of users and hobbies, and provide decision-making basis for e-commerce enterprises, this paper designs an adaptive Web Recommendation System Framework Self-Adaptive Websites Recommendation System. It is divided into two parts: offline parts and online components. The former includes data collection, preprocessing and frequent access pattern mining. The latter generates recommendation sets based on existing mining rules and user’s current access behaviour of offline components, and realizes adaptive online recommendation service. Taking the university library as an example, this paper uses the sliding window method to obtain the current user access path, then use association rule algorithm based on aggregation tree to generate association rule set. After getting association rule set, we use recommendation set generation algorithm to generate recommendation set. The results show that both theoretical analysis and experiment indicate that the method is effective and feasible.

A Recommender System for Library Based on Hadoop Ecosystem

With the rapid development of network and information technology, big data already exists in various fields. Its main features include large amount of data (Volume), speed (Velocity) and diversity (Variety). The information system of library also has the characteristics of big data which have a large number of collected books, readers, and diverse resources. Because of the era of big data, libraries need to assist the reader to rapidly get the appropriate information from a large number of collected resources in the library information system. It is an important issue to establish the suitable recommender system in order to recommend readers to the related library resources and to enhance the usage of library resources. In this paper, a recommender system for library based on Hadoop Ecosystem is proposed. First, it uses Hadoop ecosystem to import data from the information system of library. Furthermore, the association rule and parallel CLARANS are implemented in Hadoop platform for the library recommender system. The proposed approach can assist readers to find the suitable resources in library.

Search-based software library recommendation using multi-objective optimization

Context: Software library reuse has significantly increased the productivity of software developers, reduced time-to-market and improved software quality and reusability. However, with the growing number of reusable software libraries in code repositories, finding and adopting a relevant software library becomes a fastidious and complex task for developers.Objective: In this paper, we propose a novel approach called LibFinder to prevent missed reuse opportunities during software maintenance and evolution. The goal is to provide a decision support for developers to easily find “useful” third-party libraries to the implementation of their software systems.Method: To this end, we used the non-dominated sorting genetic algorithm (NSGA-II), a multi-objective search-based algorithm, to find a trade-off between three objectives : 1) maximizing co-usage between a candidate library and the actual libraries used by a given system, 2) maximizing the semantic similarity between a candidate library and the source code of the system, and 3) minimizing the number of recommended libraries.Results: We evaluated our approach on 6083 different libraries from Maven Central super repository that were used by 32,760 client systems obtained from Github super repository. Our results show that our approach outperforms three other existing search techniques and a state-of-the art approach, not based on heuristic search, and succeeds in recommending useful libraries at an accuracy score of 92%, precision of 51% and recall of 68%, while finding the best trade-off between the three considered objectives. Furthermore, we evaluate the usefulness of our approach in practice through an empirical study on two industrial Java systems with developers. Results show that the top 10 recommended libraries was rated by the original developers with an average of 3.25 out of 5.Conclusion: This study suggests that (1) library usage history collected from different client systems and (2) library semantics/content embodied in library identifiers should be balanced together for an efficient library recommendation technique.

Neural Network Classification for user Profile Learning over Digital Library Recommendation Engine

Objectives: To propose a hybrid recommendation engine to make perfect order of recommendations for online digital library portals. Methods/Statistical Analysis: The proposed model combines the content-based learning based upon the neutralized factors along with the collaborative learning for producing the recommendations on the basis of the interuser similarity, which is learned from the user’s profile representation vector. The hybrid recommendation algorithm is intended to produce more relevant recommendations for the digital library users. Findings: The proposed has been tested over the different sizes of the data. The proposed model has been designed for the discovery of the similar entities using the neural network classification and the top five entities are utilized for the calculation of the missing profile values to compute the recommendations over the digital library systems. The proposed model’s performance has been analyzed and studied using the statistical performance measuring parameters which elaborates the system performance from various perspectives. The experimental results have shows the robust performance of the proposed model in the terms of mentioned parameters. Application/Improvements: The proposed model has been improved the recommendations by the means of the calculating the inter user relevance to evaluate the recommendations for the user in the scope.

A statistical approach for modeling inter-document semantic relationships in digital libraries

E-Learning repositories and digital libraries are fast becoming important sources for gathering information and learning material. Such systems must therefore provide services to support the learning needs of their users. When a retrieval system shows how its documents relate to each other semantically, a user gets the liberty to choose from different material, and direct his/her study in a focused manner. This calls for a model that identifies types of document relationships, that need to address different aspects of learning. This article defines three such types and a unique statistical model that can automatically identify them in technical/scientific documents. The model defines measures to quantify the degree of relatedness based on distinct statistical patterns exhibited by the common terms in a pair of documents. This approach does not strictly require a knowledge base or hypertext for identifying the characteristic relationship between two documents. Such a statistical model can be extended to build further relatedness types and can be used alongside various other techniques in digital library recommendation engines. Our experiments over a large number of technical documents show that our techniques effectively extract the different types of relationships between documents.