Search results

This study aims to determine the most similar set of recommendation books to the user selections in LibraryThing.

For this purpose, 30,000 tags related to History on the LibraryThing have been selected. Their tags and the tags of the related recommended books were extracted from three different recommendations sections on LibraryThing. Then, four similarity criteria of Jaccard coefficient, Cosine similarity, Dice coefficient and Pearson correlation coefficient were used to calculate the similarity between the tags. To determine the most similar recommended section, the best similarity criterion had to be determined first. So, a researcher-made questionnaire was provided to History experts.

The results showed that the Jaccard coefficient, with a frequency of 32.81, is the best similarity criterion from the point of view of History experts. Besides, the degree of similarity in LibraryThing recommendations section according to this criterion is equal to 0.256, in the section of books with similar library subjects and classifications is 0.163 and in the Member recommendations section is 0.152. Based on the findings of this study, the LibraryThing recommendations section has succeeded in introducing the most similar books to the selected book compared to the other two sections.

To the best of the authors’ knowledge, itis for the first time, three sections of LibraryThing recommendations are compared by four different similarity criteria to show which sections would be more beneficial for the user browsing. The results showed that machine recommendations work better than humans.

This study aims to investigate redundant information in mandatory non-financial reports (NFRs) demanded by regulators, focusing primarily on overlapping disclosures in a new Indian sustainability reporting (SR) framework.

The study sample comprised NIFTY100 listed entities that published SR voluntarily during 2021–2022. The authors used content analysis and cosine similarity techniques to conceptually compare redundancy in SR disclosures with non-financial disclosures.

The findings reveal an information overlap in SR disclosure with other NFRs disclosures. The disclosures of Directors’ Report have higher cosine similarity scores at the firm level with SR, followed by the Management Discussion and Analysis report, Corporate Governance report and Corporate Social Responsibility report. The additional analysis reveals that qualitative disclosures and disclosures comprising governance factors overlap more in SR.

Policymakers should look to establish relevant disclosure guidelines in the SR system, and thereby, shed light on fundamental issues to enhance future SR framework reforms.

The study highlight the need for integration and amendment in the disclosure guidelines of NFRs to improve the overall transparency of the reports.

Previous studies have examined the redundancy in annual reports and SRs from the point of view of overlapping information. To the best author’s knowledge, this is possibly among the first studies to offer insights into the repetition of disclosures required by regulators in statutory NFRs based on environmental, social, and governance factors through the lenses of the institutional theory.

The collaborative filtering algorithm is a classical and widely used approach in product recommendation systems. However, the existing algorithms rely mostly on common ratings of items and do not consider temporal information about items or user interests. To solve this problem, this study proposes a new user-item composite filtering (UICF) recommendation framework by leveraging temporal semantics.

The UICF framework fully utilizes the time information of item ratings for measuring the similarity of items and takes into account the short-term and long-term interest decay for computing users’ latest interest degrees. For an item to be probably recommended to a user, the interest degrees of the user on all the historically rated items are weighted by their similarities with the item to be recommended and then added up to predict the recommendation degree.

Comprehensive experiments on the MovieLens and KuaiRec datasets for user movie recommendation were conducted to evaluate the performance of the proposed UICF framework. Experimental results show that the UICF outperformed three well-known recommendation algorithms Item-Based Collaborative Filtering (IBCF), User-Based Collaborative Filtering (UBCF) and User-Popularity Composite Filtering (UPCF) in the root mean square error (RMSE), mean absolute error (MAE) and F1 metrics, especially yielding an average decrease of 11.9% in MAE.

A UICF recommendation framework is proposed that combines a time-aware item similarity model and a time-wise user interest degree model. It overcomes the limitations of common rating items and utilizes temporal information in item ratings and user interests effectively, resulting in more accurate and personalized recommendations.

The increasing popularity of music streaming services also increases the need to customize the services for each user to attract and retain customers. Most of the music streaming services will not have explicit ratings for songs; they will have only implicit feedback data, i.e user listening history. For efficient music recommendation, the preferences of the users have to be infered, which is a challenging task.

Preferences of the users can be identified from the users' listening history. In this paper, a hybrid music recommendation system is proposed that infers features from user's implicit feedback and uses the hybrid of content-based and collaborative filtering method to recommend songs. A Content Boosted K-Nearest Neighbours (CBKNN) filtering technique was proposed, which used the users' listening history, popularity of songs, song features, and songs of similar interested users for recommending songs. The song features are taken as content features. Song Frequency–Inverse Popularity Frequency (SF-IPF) metric is proposed to find the similarity among the neighbours in collaborative filtering. Million Song Dataset and Echo Nest Taste Profile Subset are used as data sets.

The proposed CBKNN technique with SF-IPF similarity measure to identify similar interest neighbours performs better than other machine learning techniques like linear regression, decision trees, random forest, support vector machines, XGboost and Adaboost. The performance of proposed SF-IPF was tested with other similarity metrics like Pearson and Cosine similarity measures, in which SF-IPF results in better performance.

This method was devised to infer the user preferences from the implicit feedback data and it is converted as rating preferences. The importance of adding content features with collaborative information is analysed in hybrid filtering. A new similarity metric SF-IPF is formulated to identify the similarity between the users in collaborative filtering.

This study introduces a novel approach to preventing construction quality problems by examining the complex interrelations among such issues. Recognizing the overlooked coupling between problems is essential, as it can exacerbate quality issues, triggering chain reactions that compromise project success. The research justifies its focus on these interrelations by highlighting the insufficiency of traditional quality management methods, which often fail to account for interconnected quality problems in the architecture, engineering and construction (AEC) industry.

At the core of this research is the establishment of a knowledge base for construction quality issues, marking a pioneering effort to systematically organize unstructured textual data on construction quality problems and their interconnections. This base serves as a platform for the subsequent application of advanced analytical techniques. Specifically, the study leverages preprocessing, text similarity algorithms and association rule mining to dissect and illuminate the nuanced coupling relationships among construction quality issues, a facet not thoroughly explored in prior research.

The innovative analytical methodology employed here reveals significant insights into the dynamics of construction quality issue coupling. These insights not only deepen the understanding of these complex interactions but also guide the development of targeted intervention strategies. The practical applicability and effectiveness of the proposed approach are demonstrated using selected textual materials as experimental evidence. The findings show that understanding and addressing these couplings can significantly mitigate potential chain reactions of defects, thus enhancing overall project quality.

The originality of this study lies in its threefold contribution: the creation of a dedicated knowledge base for construction quality issues, the application of novel analytical methodologies to decipher coupling relationships and the extension of text analysis techniques to the realm of construction quality problem prevention. Together, these innovations open new avenues for research and practice in construction management, offering a robust framework for the systematic identification and mitigation of quality issues in construction projects.

The growing availability of naturalistic driving datasets (NDDs) presents a valuable opportunity to develop various models for autonomous driving. However, while current NDDs include data on vehicles with and without intended driving behavior changes, they do not explicitly demonstrate a type of data on vehicles that intend to change their driving behavior but do not execute the behaviors because of safety, efficiency, or other factors. This missing data is essential for autonomous driving decisions. This study aims to extract the driving data with implicit intentions to support the development of decision-making models.

According to Bayesian inference, drivers who have the same intended changes likely share similar influencing factors and states. Building on this principle, this study proposes an approach to extract data on vehicles that intended to execute specific behaviors but failed to do so. This is achieved by computing driving similarities between the candidate vehicles and benchmark vehicles with incorporation of the standard similarity metrics, which takes into account information on the surrounding vehicles' location topology and individual vehicle motion states. By doing so, the method enables a more comprehensive analysis of driving behavior and intention.

The proposed method is verified on the Next Generation SIMulation dataset (NGSim), which confirms its ability to reveal similarities between vehicles executing similar behaviors during the decision-making process in nature. The approach is also validated using simulated data, achieving an accuracy of 96.3 per cent in recognizing vehicles with specific driving behavior intentions that are not executed.

This study provides an innovative approach to extract driving data with implicit intentions and offers strong support to develop data-driven decision-making models for autonomous driving. With the support of this approach, the development of autonomous vehicles can capture more real driving experience from human drivers moving towards a safer and more efficient future.

The Confederation of Open Access Repositories (COAR) prescribes three types of controlled vocabularies for open access repositories (OARs): access rights, resource type and version type. Interestingly, COAR does not suggest a subject-specific vocabulary for organising content, whereas the subject parameter is one of the most preferred search categories used by information seekers. The purpose of the study is to investigate the use of controlled vocabularies in subject arrangement in OARs.

The study comprises eight stages. The first is to identify the total number of repositories enlisted in OpenDOAR under the social science domain in India. Next, the samples are selected, followed by data harvesting using MarcEdit OAI-PMH harvester plug-ins. The next step is to process the data and then consolidated controlled vocabulary is constructed by merging six existing thesauri. Then, a similarity matching algorithm is used to determine the usage of controlled vocabularies for subject arrangement. The last step is to evaluate the efficacy of controlled vocabulary in information retrieval.

The results revealed that subject arrangement differs largely in each repository. The study also showed that the use of controlled vocabularies in OARs for subject arrangement still needs to be standardised to enhance interoperability.

This research reflected that those controlled terms address issues, such as ambiguity, inconsistency and synonym variation, typically found with uncontrolled keywords through standardising subject metadata. This standardisation gives users a more reliable and user-friendly search experience, ultimately improving the discoverability and usability of open access content.

This study aims to develop an associative text analyzer (ATA) to support users in quickly grasping and interpreting the content of large amounts of text through text association recommendations, facilitating the identification of the contextual relationships between people, events, organization and locations for digital humanities. Additionally, by providing text summaries, the tool allows users to link between distant and close readings, thereby enabling more efficient exploration of related texts.

To verify the effectiveness of this tool in supporting exploration of historical texts, this study uses a counterbalanced design to compare the use of the digital humanities platform for Mr. Lo Chia-Lun’s Writings (DHP-LCLW) with and without the ATA to assist in exploring different aspects of text. The study investigated whether there were significant differences in effectiveness for exploring textual contexts and technological acceptance as well as used semi-structured in-depth interviews to understand the research participants’ viewpoints and experiences with the ATA.

The results of the experiment revealed that the effectiveness of text exploration using the DHP-LCLW with and without the ATA varied significantly depending on the topic of the text being explored. The DHP-LCLW with the ATA was found to be more suitable for exploring historical texts, while the DHP-LCLW without the ATA was more suitable for exploring educational texts. The DHP-LCLW with the DHP-LCLW was found to be significantly more useful in terms of perceived usefulness than the DHP-LCLW without the ATA, indicating that the research participants believed the ATA was more effective in helping them efficiently grasp the related texts and topics during text exploration.

The study’s practical implications lie in the development of an ATA for digital humanities, offering a valuable tool for efficiently exploring historical texts. The ATA enhances users’ ability to grasp and interpret large volumes of text, facilitating contextual relationship identification. Its practical utility is evident in the improved effectiveness of text exploration, particularly for historical content, as indicated by users’ perceived usefulness.

This study proposes an ATA for digital humanities, enhancing text exploration by offering association recommendations and efficient linking between distant and close readings. The study contributes by providing a specialized tool and demonstrating its perceived usefulness in facilitating efficient exploration of related texts in digital humanities.

Improving the diversity of recommendation information has become one of the latest research hotspots to solve information cocoons. Aiming to achieve both high accuracy and diversity of recommender system, a hybrid method has been proposed in this paper. This study aims to discuss the aforementioned method.

This paper integrates latent Dirichlet allocation (LDA) model and locality-sensitive hashing (LSH) algorithm to design topic recommendation system. To measure the effectiveness of the method, this paper builds three-level categories of journal paper abstracts on the Web of Science platform as experimental data.

(1) The results illustrate that the diversity of recommended items has been significantly enhanced by leveraging hashing function to overcome information cocoons. (2) Integrating topic model and hashing algorithm, the diversity of recommender systems could be achieved without losing the accuracy of recommender systems in a certain degree of refined topic levels.

The hybrid recommendation algorithm developed in this paper can overcome the dilemma of high accuracy and low diversity. The method could ameliorate the recommendation in business and service industries to address the problems of information overload and information cocoons.

The aim of this study is to investigate the application of advanced language models, particularly ChatGPT-4, in identifying and utilizing industrial symbiosis opportunities within the circular economy. It examines how the model can aid in promoting sustainable industrial practices by processing data from the MAESTRI project database, which includes various symbiotic relationships, as well as randomly selected waste codes not included in the database. The research involves structured queries related to industrial symbiosis, circular economy, waste codes and potential opportunities. By assessing the model’s accuracy in response generation, the study seeks to uncover both the capabilities and limitations of the language model in resource efficiency and waste reduction, emphasizing the need for ongoing refinement and expert oversight.

The study adopts a mixed-methods approach, combining qualitative and quantitative analyses to explore the potential of ChatGPT-4 in identifying industrial symbiosis opportunities. Data from the EU-funded MAESTRI project database, which includes existing symbiotic relationships, as well as randomly selected waste codes not included in the database, are used as the primary sources. The language model is queried with structured questions on industrial symbiosis, circular economy and specific waste codes utilizing the model’s advanced functions such as file upload. Responses are evaluated by comparing them with the MAESTRI database and official European Waste Catalogue (EWC) codes.

The study finds that ChatGPT-4 possesses a solid understanding of fundamental concepts related to industrial symbiosis and the circular economy. However, it encounters challenges in accurately describing EWC codes, with a notable portion of descriptions found to be incorrect. Despite these inaccuracies, the model shows potential in suggesting symbiotic opportunities, although its effectiveness is limited. Interestingly, the study reveals that the model can occasionally identify correct symbiotic relationships even with initial inaccuracies. These findings highlight the need for expert oversight and further development of the language model to improve its utility in complex, regulated fields like industrial symbiosis.

This study’s originality lies in its exploration of advanced language models, particularly ChatGPT-4, for identifying industrial symbiosis opportunities within the circular economy framework. Unlike previous research, which primarily focuses on specific sectors and AI’s role in general resource efficiency, this study specifically examines the capabilities and limitations of the language model in handling specialized and regulated information, such as EWC codes across various sectors. It employs a novel approach by comparing AI-generated responses with an established symbiosis database, which is comprehensive and spans all sectors rather than being limited to a single industry, as well as with randomly selected waste codes not included in the database. The study contributes to understanding how AI tools can support sustainable industrial practices, emphasizing the importance of refining these models for practical applications in environmental and industrial contexts.