Search results

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.

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 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.

Today’s in-demand skills may not be needed tomorrow. As companies are adopting a new group of technologies, they are in huge need of information technology (IT) professionals who can fill various IT positions with a mixture of technical and problem-solving skills. This study aims to adopt a sematic analysis approach to explore how the US Information Systems (IS) programs meet the challenges of emerging IT topics.

This study considers the application of a hybrid semantic analysis approach to the analysis of IS higher education programs in the USA. It proposes a semantic analysis framework and a semantic analysis algorithm to analyze and evaluate the context of the IS programs. To be more specific, the study uses digital transformation as a case study to examine the readiness of the IS programs in the USA to meet the challenges of digital transformation. First, this study developed a knowledge pool of 15 principles and 98 keywords from an extensive literature review on digital transformation. Second, this study collects 4,093 IS courses from 315 IS programs in the USA and 493,216 scientific publication records from the Web of Science Core Collection.

Using the knowledge pool and two collected data sets, the semantic analysis algorithm was implemented to compute a semantic similarity score (DxScore) between an IS course’s context and digital transformation. To present the credibility of the research results of this paper, the state ranking using the similarity scores and the state employment ranking were compared. The research results can be used by IS educators in the future in the process of updating the IS curricula. Regarding IT professionals in the industry, the results can provide insights into the training of their current/future employees.

This study explores the status of the IS programs in the USA by proposing a semantic analysis framework, using digital transformation as a case study to illustrate the application of the proposed semantic analysis framework, and developing a knowledge pool, a corpus and a course information collection.

The purpose of this paper is to investigate the impact of two dimensions of technological relatedness, namely technological similarity and complementarity, on collaborative performance, plus the mediating role of collaboration network stickiness and the moderating role of partner expertise and geographical distance in interfirm collaboration contexts.

This study takes Chinese Scientific and Technological Achievements (STA) of inter-firm collaboration in five high-tech fields in 2010–2020 as the sample and uses OLS regression to test the hypothesis.

Technological similarity and complementarity positively affect collaborative performance. Partner expertise negatively moderates the relationship between similarity, complementarity and collaborative performance. Geographical distance positively moderates the relationship between similarity and collaborative performance while negatively moderates that between complementarity and collaborative performance. Collaboration network stickiness partly mediates the relationship between similarity and collaborative performance.

This study expands literature on inter-firm collaboration, especially research on the antecedents of collaborative performance. Moreover, this study not only compensates for lack of empirical analysis in partner selection research, but also utilizes second-hand data to enhance the objectivity of analysis. Additionally, we enrich the research on the moderating role of partner expertise and geographical distance as well as the mediating role of collaboration network stickiness.

Positive effect of knowledge sharing (KS) on innovation has come to the fore and government-supported innovation and mentoring communities or mentor networks have become widespread. This article aims to examine the community connectedness and mentors' preferences for professional competency-based KS of such innovation community of practice networks (CoPNs).

The paper constructs a directed weighted CoPN model with a node-attribute-based novel fingerprint edge weights. Based on the CoPN, Social Network Analysis (SNA) metrics and measures including Giant Component (GC) were proposed and analyzed to identify mentors' connectedness preferences. The fingerprint was proposed as a novel binarized node attribute of competence. Jaccard similarity of fingerprints was proposed as edge weights to reveal correlations between competences and preferences for KS.

The work opted to conduct a survey of 28 innovation mentors to measure a CoPN. Both a name generator question and a second set of questions were employed to invite respondents to name their collaborators and indicate their professional competence. SNA metrics result in differing values for GC and the rest, which lead us to focus on GC to reveal salient metrics of connectedness. Jaccard similarity analysis results on GC demonstrate that mentors collaborate in an interdisciplinary manner.

Based on the CoPN, the methods proposed may be effective in predicting preferred relationships for interdisciplinary collaborations, providing the managers with an analytical decision support tool for KS in practice.

Anecdotal evidence suggests that casting actors with similar facial features in a movie can pose challenges in foreign markets, hindering the audience's ability to recognize and remember characters. Extending developments in the literature on the cross-race effect, we hypothesize that facial similarity – the extent to which the actors starring in a movie share similar facial features – will reduce the country-level box-office performance of US movies in East and South-East Asia (ESEA) countries.

We assembled data from various secondary data sources on US non-animation movies (2012–2021) and their releases in ESEA countries. Combining the data resulted in a cross-section of 2,616 movie-country observations.

Actors' facial similarity in a US movie's cast reduces its box-office performance in ESEA countries. This effect is weakened as immigration in the country, internet penetration in the country and star power increase and strengthened as cast size increases.

This first study on the effects of cast's facial similarity on box-office performance represents a novel extension to the growing literature on the antecedents of movies' box-office performance by being at the intersection of the two literature streams on (1) the box-office effects of cast characteristics and (2) the antecedents, in general, of box-office performance in the ESEA region.

This review article is focused on the following research questions: RQ1: What are the methods used by authors to collect data in order to evaluate one's profile? RQ2: What are the classification algorithms and ranking metrics used to give suggestions to users? RQ3: How effective are these algorithms and metrics identified in RQ2?

There are four major systematic review phases being carried out in this survey, namely the formulation of research questions, conducting the review, which includes the selection of articles and appraising evidence quality, data extraction and narrative data synthesis.

Collecting from primary sources is more personalized and relevant. Embedded skill sets that have a considerable impact on one’s career aspirations could be mined from secondary sources. A hybrid recommender system helped mitigate the limitations of both. The effectiveness of the models depends not only rely on the filtering techniques used but also on the metrics used to measure similarity and the frequency of words or phrases used in a document.

The study benefits internship program coordinators of a university aiming to develop a recommender or matching system platform for their students. The content of the study may shed a light on how university decision-makers can explore options on what are the techniques or algorithms to be integrated. One of the advantages of internship or industrial training programs is that they would help students align them with their career goals. Research studies have discussed other RS filtering techniques apart from the three major filtering techniques.

The outcome of the study, which is a recommendation system to match a student's profile with the knowledge and skills being sought by organizations, may help ease the challenges encountered by both parties. The study benefits internship coordinators of a university who are planning to create a recommendation system, an innovative project to be used in teaching and learning.

Internship programs can help a student grow personally and professionally. A university student looking for internship opportunities can find it a daunting task to undertake, as there is a vast pool of opportunities offered in the market. The confidence levels needed to match their knowledge, skills and career goals with the job descriptions (JDs) could be challenging. The same holds with companies, as finding the right people for the right job is a tough endeavor. The main objective of conducting this study is to identify models implemented in recommendation systems to give and/or rank suggestions given to users.

While surveys regarding recommender systems (RS) exist, there are gaps in the presentation of various data collection methods and the comparison of recommendation filtering techniques used for both primary and secondary sources of data. Most recommendation systems for internship programs are intended for European universities and not much for Southeast Asia. There are also a limited number of comparative studies or systematic review articles related to recommendation systems for internship programs offered in an Southeast Asian landscape. Systematic reviews on the usability of the proposed recommendation systems are also limited. The study presents reviews of articles, from data collection and techniques used to the usability of the proposed recommendation systems, which were presented in the articles being studied.

The current study examines a novel model that examines how the online and offline or general personality of the same person predicts social identification with the endorser in a message and their subsequent online behaviors (e.g. ad-skipping) on social media, both differentially and simultaneously.

Real-time ad-skipping behaviors were tracked and analyzed across three online experiments.

The results supported the model explicating the dual and simultaneous influence of offline and online personalities on ad-skipping behaviors. Specifically, in response to a skippable video ad, online and offline personalities respectively increase and decrease viewers’ identification with the endorser. Consequently, the higher or lower the identification, the lower or higher the rate of ad-skipping behaviors.

The current study will benefit from a larger set of real-world data (i.e. big data) to enhance the generalizability of the findings, supporting the model.

With the growing prevalence of the gap between online and offline self-identities driven by social media usage, this paper suggests that the ad message needs to address the dual influence of both online and offline identities on ad-skipping behaviors.

The current study tests a novel model that shows that the online and offline personalities of the same person concurrently influence one’s behavior on the Internet, rather than separately.

Supply chain management (SCM)-embedded valuable resources, such as capital, raw-materials, products, partners, customers and finished inventories, where the evaluation of environmental texture and flexibilities are needed to perceive sustainability. The present study aims to identify and evaluate the directory of green and agile (G-A) attributes based on decision support framework (DSF) for identifying dominating measures in SCM.

DSF is developed by exploiting generalized interval valued trapezoidal fuzzy numbers (GIVTFNs). Two technical approaches, i.e. degree of similarity approach (DSA) and distance approach (DA) under the extent boundaries of GIVTFNs, are implicated for data analytics and for recognizing constructive G-A measures based on comparative study for robust decision. A fuzzy-based performance indicator, i.e. fuzzy performance important index (FPII), is presented to enumerate the weak and strong G-A characteristics to manage knowledge risks in allied business environment.

The modeling is illustrated from the insights of decision-makers for augmenting business value based on cognitive identification of measures, where the best performance score is identified by the “sustainable packaging” under the traits of green supply chain management (GSCM). “The use of Web-based applications” under the traits of agile supply chain management (ASCM) and “Outsourcing flexibility” under traits of ASCM is found as the second and third most significant performance characteristics for business sustainability. Additionally, the “Reutilization (recycling) and reprocessing” under GSCM in manufacturing and “Responsiveness and speed toward customers needs” under ASCM are found difficult in attainment.

The G-A evaluation will assist in attaining performance excellence in day-to-day operations and overall functioning. The outcomes will help executives to plan strategic objectives and attaining success.

To reinforce the capabilities of SCM, wide extent of G-A dimensions are presented, concept of FPII is reported to manage knowledge risks based on identification of strong attributes and two technical approaches, i.e. DSA and DA under GIVTFNs are presented for attaining robust decision and directing managerial decision-making process.