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.

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.

Mouth segmentation is one of the challenging tasks of development in lip reading applications due to illumination, low chromatic contrast and complex mouth appearance. Recently, deep learning methods effectively solved mouth segmentation problems with state-of-the-art performances. This study presents a modified Mobile DeepLabV3 based technique with a comprehensive evaluation based on mouth datasets.

This paper presents a novel approach to mouth segmentation by Mobile DeepLabV3 technique with integrating decode and auxiliary heads. Extensive data augmentation, online hard example mining (OHEM) and transfer learning have been applied. CelebAMask-HQ and the mouth dataset from 15 healthy subjects in the department of rehabilitation medicine, Ramathibodi hospital, are used in validation for mouth segmentation performance.

Extensive data augmentation, OHEM and transfer learning had been performed in this study. This technique achieved better performance on CelebAMask-HQ than existing segmentation techniques with a mean Jaccard similarity coefficient (JSC), mean classification accuracy and mean Dice similarity coefficient (DSC) of 0.8640, 93.34% and 0.9267, respectively. This technique also achieved better performance on the mouth dataset with a mean JSC, mean classification accuracy and mean DSC of 0.8834, 94.87% and 0.9367, respectively. The proposed technique achieved inference time usage per image of 48.12 ms.

The modified Mobile DeepLabV3 technique was developed with extensive data augmentation, OHEM and transfer learning. This technique gained better mouth segmentation performance than existing techniques. This makes it suitable for implementation in further lip-reading applications.

This study aims to elucidate the dynamics of social media discourse during global health events, specifically investigating how users across different platforms perceive, react to and engage with information concerning such crises.

A mixed-method approach was employed, combining both quantitative and qualitative data collection. Initially, thematic analysis was applied to a data set of social media posts across four major platforms over a 12-month period. This was followed by sentiment analysis to discern the predominant emotions embedded within these communications. Statistical tools were used to validate findings, ensuring robustness in the results.

The results showcased discernible thematic and emotional disparities across platforms. While some platforms leaned toward factual information dissemination, others were rife with user sentiments, anecdotes and personal experiences. Overall, a global sense of concern was evident, but the ways in which this concern manifested varied significantly between platforms.

The primary limitation is the potential non-representativeness of the sample, as only four major social media platforms were considered. Future studies might expand the scope to include emerging platforms or non-English language platforms. Additionally, the rapidly evolving nature of social media discourse implies that findings might be time-bound, necessitating periodic follow-up studies.

Understanding the nature of discourse on various platforms can guide health organizations, policymakers and communicators in tailoring their messages. Recognizing where factual information is required, versus where sentiment and personal stories resonate, can enhance the efficacy of public health communication strategies.

The study underscores the societal reliance on social media for information during crises. Recognizing the different ways in which communities engage with, and are influenced by, platform-specific discourse can help in fostering a more informed and empathetic society, better equipped to handle global challenges.

This research is among the first to offer a comprehensive, cross-platform analysis of social media discourse during a global health event. By comparing user engagement across platforms, it provides unique insights into the multifaceted nature of public sentiment and information dissemination during crises.

In the era of big data, various industries are generating large amounts of text data every day. Simplifying and summarizing these data can effectively serve users and improve efficiency. Recently, zero-shot prompting in large language models (LLMs) has demonstrated remarkable performance on various language tasks. However, generating a very “concise” multi-document summary is a difficult task for it. When conciseness is specified in the zero-shot prompting, the generated multi-document summary still contains some unimportant information, even with the few-shot prompting. This paper aims to propose a LLMs prompting for multi-document summarization task.

To overcome this challenge, the authors propose chain-of-event (CoE) prompting for multi-document summarization (MDS) task. In this prompting, the authors take events as the center and propose a four-step summary reasoning process: specific event extraction; event abstraction and generalization; common event statistics; and summary generation. To further improve the performance of LLMs, the authors extend CoE prompting with the example of summary reasoning.

Summaries generated by CoE prompting are more abstractive, concise and accurate. The authors evaluate the authors’ proposed prompting on two data sets. The experimental results over ChatGLM2-6b show that the authors’ proposed CoE prompting consistently outperforms other typical promptings across all data sets.

This paper proposes CoE prompting to solve MDS tasks by the LLMs. CoE prompting can not only identify the key events but also ensure the conciseness of the summary. By this method, users can access the most relevant and important information quickly, improving their decision-making processes.

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 density peak clustering algorithm (DP) is proposed to identify cluster centers by two parameters, i.e. ρ value (local density) and δ value (the distance between a point and another point with a higher ρ value). According to the center-identifying principle of the DP, the potential cluster centers should have a higher ρ value and a higher δ value than other points. However, this principle may limit the DP from identifying some categories with multi-centers or the centers in lower-density regions. In addition, the improper assignment strategy of the DP could cause a wrong assignment result for the non-center points. This paper aims to address the aforementioned issues and improve the clustering performance of the DP.

First, to identify as many potential cluster centers as possible, the authors construct a point-domain by introducing the pinhole imaging strategy to extend the searching range of the potential cluster centers. Second, they design different novel calculation methods for calculating the domain distance, point-domain density and domain similarity. Third, they adopt domain similarity to achieve the domain merging process and optimize the final clustering results.

The experimental results on analyzing 12 synthetic data sets and 12 real-world data sets show that two-stage density peak clustering based on multi-strategy optimization (TMsDP) outperforms the DP and other state-of-the-art algorithms.

The authors propose a novel DP-based clustering method, i.e. TMsDP, and transform the relationship between points into that between domains to ultimately further optimize the clustering performance of the DP.

In recent years patents have become a very popular data source for forecasting technological changes. However, since a vast amount of patents are “worthless” (Moore, 2005), there is a need to identify the promising ones. For this purpose, previous approaches have mainly used bibliographic data, thus neglecting the benefits of textual data, such as instant accessibility at patent disclosure. To leverage these benefits, this study aims to develop an approach that uses textual patent data for predicting promising patents.

For the identification of promising patents, the authors propose a novel approach which combines link prediction with textual patent data. Thereby the authors are able to predict the emergence of hitherto unmentioned bigrams. By mapping these future bigrams to recent patents, the authors are able to distinguish between promising and nonpromising patents. To validate this approach, the authors apply the methodology to the case example of camera technology.

The authors identify stochastic gradient descent as a suitable algorithm with both a receiver operating characteristic area under curve score and a positive predictive value of 78%, which outperforms chance by a factor of two. In addition, the authors present promising camera patents for diverse application fields, such as cameras for surgical systems, cameras for rearview vision systems in vehicles or light amplification by stimulated emission of radiation detection and ranging cameras for three-dimensional imaging.

This study contributes in at least three directions to scholarship. First, the authors introduce a novel approach by combining link prediction with textual patent analysis and, in this way, leverage the benefits of both worlds. Second, the authors add to all theories that regard novel technologies as a recombination of existing technologies in presenting word combinations from textual data as a suitable instrument for revealing recombination in patents. And third, the approach can be used by scholars as a complementary or even integrative tool with conventional forecasting methods like the Delphi technique or Scenario planning.

At least three practical implications arise from the study. First, incumbent firms of a technology branch can use this approach as an early-warning system to identify technological change and to identify opportunities related to their company’s technological competence and provide inspiration for new ideas. Second, companies seeking to tap into new markets may also be interested in the approach as managers could anticipate whether their company’s technological competences are in line with upcoming trends. Third, the approach may be used as a supportive tool for various purposes, such as investment decisions or technology life cycle analysis.

The approach introduces textual patent data as suitable means for forecasting activities. As the statistical validation reveals, the promising patents identified by the approach are cited significantly more often than patents with less promising prospects.