KG4CraSolver: Recommending Crash Solutions via Knowledge Graph

Knowledge graphs have emerged as a transformative tool in enhancing personalized recommendation systems. By integrating diverse datasets into a structured semantic network, knowledge graphs offer a holistic view of relationships and entities that can significantly improve the relevance and accuracy of recommendations. Unlike traditional recommendation algorithms that rely primarily on user behaviour and item similarity, knowledge graphs leverage contextual information and complex interconnections among entities to deliver more nuanced and context-aware suggestions. This abstract explores the pivotal role of knowledge graphs in advancing personalized recommendation systems, focusing on their ability to capture intricate relationships between users, items, and attributes. By mapping out these relationships, knowledge graphs facilitate a deeper understanding of user preferences and item characteristics, enabling the generation of more tailored and precise recommendations. Additionally, the incorporation of external knowledge sources into the graph can further enrich the recommendation process, leading to enhanced user satisfaction and engagement. The paper reviews various methodologies for integrating knowledge graphs into recommendation systems, including graph-based algorithms and machine learning techniques. It also examines real-world applications and case studies where knowledge graphs have demonstrated substantial improvements in recommendation quality. Ultimately, the utilization of knowledge graphs represents a significant leap forward in personalizing user experiences, offering a promising avenue for future research and development in the field of recommendation systems.

While there has been a trend in the last decades for publishing large-scale and highly-interconnected Knowledge Graphs (KGs), their users often get overwhelmed by the task of understanding their content as a result of their size and complexity. Data profiling approaches have been proposed to summarize large KGs into concise and meaningful representations, so that they can be better explored, processed, and managed. Profiles based on schema patterns represent each triple in a KG with its schema-level counterpart, thus covering the entire KG with profiles of considerable size. In this paper, we provide empirical evidence that profiles based on schema patterns, if explored with suitable mechanisms, can be useful to help users understand the content of big and complex KGs. ABSTAT provides concise pattern-based profiles and comes with faceted interfaces for profile exploration. Using this tool we present a user study based on query completion tasks. We demonstrate that users who look at ABSTAT profiles formulate their queries better and faster than users browsing the ontology of the KGs. The latter is a pretty strong baseline considering that many KGs do not even come with a specific ontology to be explored by the users. To the best of our knowledge, this is the first attempt to investigate the impact of profiling techniques on tasks related to knowledge graph understanding with a user study.

Community answer generation based on knowledge graph

Knowledge graphs (KGs) are powerful tools for representing and reasoning over structured information. Their main components include schema, identity, and context. While schema and identity matching are well-established in ontology and entity matching research, context matching remains largely unexplored. This is particularly important because real-world KGs often vary significantly in source, size, and information density—factors not typically represented in the datasets on which current entity matching methods are evaluated. As a result, existing approaches may fall short in scenarios where diverse and complex contexts need to be integrated. To address this gap, we propose a novel KG integration method consisting of label matching and triple matching. We use string manipulation, fuzzy matching, and vector similarity techniques to align entity and predicate labels. Next, we identify mappings between triples that convey comparable information, using these mappings to improve entity-matching accuracy. Our approach demonstrates competitive performance compared to leading systems in the OAEI competition and against supervised methods, achieving high accuracy across diverse test cases. Additionally, we introduce a new dataset derived from the benchmark dataset to evaluate the triple-matching step more comprehensively.

Software bugs continuously emerge during the process of software evolution. With the increasing size and complexity of software, bug fixing becomes increasingly more difficult. Bug and commit data of open source projects, Q&A documents and other software resources contain a sea of bug knowledge which can be utilized to help developers understand and fix bugs. Existing work focuses on data mining from a certain software resource in isolation to assist in bug fixing, which may reduce the efficiency of bug fixing. How to obtain, organize and understand bug knowledge from multi-source software data is an urgent problem to be solved. In order to solve this problem, we utilize knowledge graph (KG) technology to explore the deep semantic and structural relationships in the multi-source software data, propose effective search and recommendation techniques based on the knowledge graph, and design a bug-fix knowledge question & answering system to assist developers in intelligent software bug fixing. At present, we have designed a bug knowledge graph construction framework, proposed the identification principles and methods for bug knowledge entities and relationships, constructed a preliminary knowledge graph based on the bug repository. In the following work, we will further improve the knowledge graph, complete the knowledge graph fusion of multi-source database, comprehend bug knowledge through knowledge reasoning, utilize the collaborative search and recommendation technology for bug-fixing knowledge question and answering.

Developers' social information seeking on the Web is unable to benefit from the recent significant advances of semantics-oriented applications, such as knowledge graph and direct answers. This is largely because existing approaches to analyzing software engineering social content, such as the discussions on Stack Overflow, 1) treat softwarespecific entities in the same way as other textual content, and 2) fall short to consider the semantic linkages between software knowledge. In this thesis, we perform a pioneering study towards the long-term goal of enabling domain-specific knowledge graph and semantic search in software engineering. Using the developer-generated content on Stack Overflow, we formulate a series of research problems that are the key steps for achieving this goal. These include: 1) we investigate the online knowledge connection in software engineering by analyzing the knowledge network formed by Stack Overflow users' URL sharing activities. Through this study, we obtain an overall understanding of the domain knowledge organization, correlation and evolution, which inspires further research on extracting and linking software engineering knowledge. 2) we propose semi-supervised methods for extracting software-specific named entities, such as API mentions, from informal natural language text. 3) we develop automated techniques to link semantically linkable knowledge at document-level, and to link a recognized API mention to its fully qualified form as appeared in the API documentation at entity-level.

Library migration, which replaces the current library with a different one to retain the same software behavior, is common in software evolution. An essential part of this is finding an analogous API for the desired functionality. However, due to the multitude of libraries/APIs, manually finding such an API is time-consuming and error-prone. Researchers created automated analogical API recommendation techniques, notably documentation-based methods. Despite potential, these methods have limitations, e.g., incomplete semantic understanding in documentation and scalability issues. In this study, we present KGE4AR, a novel documentation-based approach using knowledge graph (KG) embedding for recommending analogical APIs during library migration. KGE4AR introduces a unified API KG to comprehensively represent documentation knowledge, capturing high-level semantics. It further embeds this unified API KG into vectors for efficient, scalable similarity calculation. We assess KGE4AR with 35,773 Java libraries in two scenarios, with and without target libraries. KGE4AR notably outperforms state-of-the-art techniques (e.g., 47.1%-143.0% and 11.7%-80.6% MRR improvements), showcasing scalability with growing library counts.

Massive Open Online Courses (MOOCs) have gained popularity in the technology-enhanced learning (TEL) domain. To enhance the learning experience in MOOCs, educational recommender systems (ERSs) can play a crucial role by suggesting courses or learning materials that align with students' knowledge states. Thereby, understanding a student's learning needs and predicting knowledge concepts that the student might be interested in are important to provide effective recommendations. Inspired by the superior ability of knowledge graphs (KGs) in modeling the heterogeneous data in MOOCs and Graph Neural Networks (GNNs) in learning on graph-structured data, few works focusing on GNN-based recommendation of knowledge concepts in MOOCs have emerged recently. However, existing approaches in this domain have limitations mainly related to complexity, semantics, and transparency. To address these limitations, in this paper we propose ConceptGCN, an end-to-end framework that combines KGs, Graph Convolutional Networks (GCNs), and pre-trained transformer language model encoders (SBERT) to provide personalized and transparent recommendations of knowledge concepts in the MOOC platform CourseMapper. We conducted extensive offline experiments and an online user study (N=31), demonstrating the benefits of the ConceptGCN-based recommendation approach, in terms of several important user-centric aspects including accuracy, novelty, diversity, usefulness, overall satisfaction, use intentions, and reading intention. In particular, our results indicate that, if SBERT is used for the initial embeddings of items in the KG, a self-connection operation and a semantic similarity-based score function in the aggregation operation of GCN are not necessarily needed.

BackgroundReminiscence, a therapy that uses stimulating materials such as old photos and videos to stimulate long-term memory, can improve the emotional well-being and life satisfaction of older adults, including those who are cognitively intact. However, providing personalized reminiscence therapy can be challenging for caregivers and family members.ObjectiveThis study aimed to achieve three objectives: (1) design and develop the GoodTimes app, an interactive multimodal photo album that uses artificial intelligence (AI) to engage users in personalized conversations and storytelling about their pictures, encompassing family, friends, and special moments; (2) examine the app’s functionalities in various scenarios using use-case studies and assess the app’s usability and user experience through the user study; and (3) investigate the app’s potential as a supplementary tool for reminiscence therapy among cognitively intact older adults, aiming to enhance their psychological well-being by facilitating the recollection of past experiences.MethodsWe used state-of-the-art AI technologies, including image recognition, natural language processing, knowledge graph, logic, and machine learning, to develop GoodTimes. First, we constructed a comprehensive knowledge graph that models the information required for effective communication, including photos, people, locations, time, and stories related to the photos. Next, we developed a voice assistant that interacts with users by leveraging the knowledge graph and machine learning techniques. Then, we created various use cases to examine the functions of the system in different scenarios. Finally, to evaluate GoodTimes’ usability, we conducted a study with older adults (N=13; age range 58-84, mean 65.8 years). The study period started from January to March 2023.ResultsThe use-case tests demonstrated the performance of GoodTimes in handling a variety of scenarios, highlighting its versatility and adaptability. For the user study, the feedback from our participants was highly positive, with 92% (12/13) reporting a positive experience conversing with GoodTimes. All participants mentioned that the app invoked pleasant memories and aided in recollecting loved ones, resulting in a sense of happiness for the majority (11/13, 85%). Additionally, a significant majority found GoodTimes to be helpful (11/13, 85%) and user-friendly (12/13, 92%). Most participants (9/13, 69%) expressed a desire to use the app frequently, although some (4/13, 31%) indicated a need for technical support to navigate the system effectively.ConclusionsOur AI-based interactive photo album, GoodTimes, was able to engage users in browsing their photos and conversing about them. Preliminary evidence supports GoodTimes’ usability and benefits cognitively intact older adults. Future work is needed to explore its potential positive effects among older adults with cognitive impairment.

Automated grammar error diagnosis remains challenging due to the complexity of syntactic structures and semantic dependencies in natural language. This study proposes a novel framework that integrates Graph Convolutional Networks (GCNs) with domain-specific knowledge graphs for enhanced English grammar error detection and correction. The approach constructs sentence-level dependency graphs to explicitly model syntactic relationships, while a multi-layered grammar knowledge graph systematically organizes grammatical concepts, error taxonomies, and correction strategies. Multi-layer graph convolutions propagate contextual information across syntactic dependencies, and attention mechanisms dynamically weight node representations for diagnostic relevance. Knowledge graph integration enriches neural representations with structured linguistic knowledge, enabling both accurate error detection and interpretable feedback generation. Experimental evaluation on CoNLL-2014, JFLEG, and BEA-2019 benchmark datasets demonstrates marked improvements, achieving F1-scores of 0.6484, 0.6719, and 0.6367 respectively, outperforming the strongest baseline BERT+BiLSTM by approximately 8.8% on CoNLL-2014 and the competitive GECToR sequence-tagging system by 4.4%, with all gains confirmed as statistically significant through bootstrap resampling. The framework proves especially effective at identifying syntactic errors such as verb tense inconsistencies and subject-verb agreement violations. We believe this research pushes graph-based natural language processing forward by connecting data-driven learning with explicit grammatical knowledge, offering diagnostic tools with promising pedagogical potential for language education-though further user studies are needed to fully validate their educational effectiveness.

We witness an unprecedented proliferation of knowledge graphs that record millions of entities and their relationships. While knowledge graphs are structure-flexible and content-rich, they are difficult to use. The challenge lies in the gap between their overwhelming complexity and the limited database knowledge of non-professional users. If writing structured queries over “simple” tables is difficult, complex graphs are only harder to query. As an initial step toward improving the usability of knowledge graphs, we propose to query such data by example entity tuples, without requiring users to form complex graph queries. Our system, Graph Query By Example ( $\mathsf {GQBE}$ ), automatically discovers a weighted hidden maximum query graph based on input query tuples, to capture a user’s query intent. It then efficiently finds and ranks the top approximate matching answer graphs and answer tuples. We conducted experiments and user studies on the large Freebase and DBpedia datasets and observed appealing accuracy and efficiency. Our system provides a complementary approach to the existing keyword-based methods, facilitating user-friendly graph querying. To the best of our knowledge, there was no such proposal in the past in the context of graphs.

This paper presents a novel, graph embedding based recommendation technique. The method operates on the knowledge graph, an information representation technique alloying content-based and collaborative information. To generate recommendations, a two dimensional embedding is developed for the knowledge graph. As the embedding maps the users and the items to the same vector space, the recommendations are then calculated on a spatial basis. Regarding to the number of cold start cases, precision, recall, normalized Cumulative Discounted Gain and computational resource need, the evaluation shows that the introduced technique delivers a higher performance compared to collaborative filtering on top-n recommendation lists. Our further finding is that graph embedding based methods show a more stable performance in the case of an increasing amount of user preference information compared to the benchmark method.

Knowledge graphs are graph-structured knowledge bases containing abundant entities and relations among the entities. Entity exploration can help users understand the overall structure of knowledge graphs, as well as find the entities of interest in an exploratory manner. Being different from typical entity-centric search whose goal is to retrieve the most related entities for a user’s specific need, the related entities that present diverse aspects are preferred for user’s ambiguous needs in entity exploration. In this paper, we propose a novel diversity-aware entity exploration approach based on random walk model, which naturally mimics human conceptual exploration by surfing a class association graph. This model leverages the diversity, representativeness and relatedness of entity classes to rank these classes in a unified way. Furthermore, for each top ranked class, the associated entities are ranked by combining their diversity and popularity. We compare our algorithm with four baseline algorithms and the experimental results indicate that it outperforms baselines. Furthermore, we conduct a task-based user study to evaluate our approach and the experimental results show that our work provides effective support for entity exploration.

In the last years, enterprises increase their effort to collect large amounts of data from many heterogeneous data sources and store it in modern architectures like data lakes. However, this approach faces different drawbacks for finding and understanding data sources. Ontology-Based Data Access (OBDA) originating from the Semantic Web enables a homogeneous access to the data sources by using a mapping, called semantic model, between a data source and a target ontology. However, OBDA requires a detailed ontology, which is usually created by ontology engineers and domain experts resulting along with high effort for designing and maintaining. To overcome these limitations, we develop an approach consisting of a knowledge graph, which features an internal growing ontology and linked data-source specific semantic models. The ontology continuously evolves on-demand based on newly added data sources along with their corresponding semantic models, which are created by domain experts. To ensure the knowledge graph's stability, we develop an intuitive user-oriented assistant and combine it with a semi-supervised evolving strategy that assists the user with the help of external knowledge bases. We evaluate accuracy and usability of our approach by conducting a user study with a heterogeneous group of participants that define semantic models upon pre-defined data sets. The results show that semantic models become more objective and consistent with our provided user assistant and thus lead to a knowledge graph with higher interconnectivity and stability.

The process of managing risks of client contracts is manual and resource-consuming, particularly so for Fortune 500 companies. As an example, Accenture assesses the risk of eighty thousand contracts every year. For each contract, different types of data will be consolidated from many sources and used to compute its risk tier. For high-risk tier contracts, a Quality Assurance Director (QAD) is assigned to mitigate or even prevent the risk. The QAD gathers and selects the recommended actions during regular portfolio review meetings to enable leadership to take the appropriate actions. In this paper, we propose to automatically personalize and contextualize actions to improve the efficacy. Our approach integrates enterprise and external data into a knowledge graph and interprets actions based on QADs’ profiles through semantic reasoning over this knowledge graph. User studies showed that QADs could efficiently select actions that better mitigate the risk than the existing approach.