Automatic Recommendation System Research Articles

Beyond User Needs: A Meaning‐Oriented Approach to Recommender Systems

This contribution is a case study of Spotify, a popular music streaming app, which uses automated recommendations to provide a better user experience to its listeners. Automated recommender systems have mostly been built around understanding user needs and user goals. Our case study presents a meaning‐oriented approach aimed at understanding what users regard as meaningful and how an automated recommender system can forge meaning and offer experiences that help develop existing connections to music and generate new ones.Following the meaning‐oriented approach inspired by Lucien Karpik (2010), we were able to better understand how different audience segments engage with music and experience music as meaningful. We identified 2 cultural engagement models that listeners use to relate to music: (1) musical engagement during which music is the focus of the experience; and (2) non‐musical engagement, during which the listener is the focus of the experience. Each engagement model uses different types of cognitive and evaluative aids, which we refer to as cues and proof points, to derive meaning from listening experiences. We also identified nine distinct types of experiences of meaning defined by distinct types of cues and proof points.The proposed approach is applicable to the study and innovation of experience‐led digital platforms and recommender systems.

Effect of automation transparency in the management of multiple unmanned vehicles

Automated decision aids can undoubtedly benefit system performance, but have the potential to provide incorrect advice, creating the possibility for automation disuse or misuse. This paper examined the extent to which increased automation transparency could improve the accuracy of automation use in a simulation of unmanned vehicle control. Participants were required to assign the best unmanned vehicle to complete missions. An automated recommender system provided advice but was not always reliable. Three levels of automation transparency were manipulated between-participants. Providing transparency regarding the reasoning underlying automated recommendations improved the accuracy of automation use, with no cost to decision time or subjective workload. Higher transparency in the form of projected decision outcome visualizations led to faster decisions, but less accurate automation use and an automation bias. Implications for the design of transparent interfaces to improve human-autonomy teaming outcomes in time-pressured environments are discussed.

KG2Rec: LSH-CF recommendation method based on knowledge graph for cloud services

With the rapid development of cloud computing paradigm and mobile devices, the number of cloud services and user interest data are growing explosively. It becomes harder for users to find suitable cloud services within satisfying response time. Thus a suitable cloud service automatic recommendation system is needed to solve the above problem. In this work, we propose KG2Rec, a novel recommendation method based on Knowledge Graph to provide users with appropriate recommendations to meet their real-time needs. The property-specific knowledge graph model is designed to model user–item and item–item bipartite relations. Based on the property-specific knowledge graph model, property-specific user–item relation features can be mined from it. Then the user–item relation features will be integrated into an improved collaborative filtering algorithm based on the local sensitive hash technique for Top-N item recommendation. Finally, we evaluate the proposed method in terms of Top-N recommendation on the MovieLens dataset, and prove it outperforms numbers of state-of-the-art recommendation systems. In addition, we prove it has well performance in term of long tail recommendation and big data processing.

On automatic recommender algorithm with regularized convolutional neural network and IR technology in the self-regulated learning process

Automatic recommendation algorithm is prominent component of many of today’s IR spectral signal educational applications. The most effective approaches for recommendation algorithm are based on the deep learning technology. The recommender system plays an important role in the field of IR spectral signal recognition. However, the infrared spectrometers often exist the problem of the low signal-to-noise and overlapped peaks. To address those issues, we propose an IR spectrum signal reconstruction approach with the framelet transform regularization. First, the famous framelet transform is introduced to reveal the difference between the overlap IR spectral signal and the high-resolution one. We find that the framelet coefficient distribution of the high-resolution IR spectral signal is sparser than that of the overlap one. Furthermore, to optimize the developed method, the alternating-direction-method-of-multipliers is introduced to calculate the IR spectral signals and the overlap function. Simulated and real experiments on the IR spectral signals illustrate that the developed method outperform the existed popular algorithms. The proposed approach is applied in the automatic recommender system that is crucial for IR spectrum teaching in the self-regulated learning process.

Topical Prescriptive Analytics System for Automatic Recommendation of Convergence Technology

This study applies text mining in scientific articles for discovery of interdisciplinary convergence technology between biotechnology (BT) and information and communication technology (ICT). For in-depth interpretation of the technologies without domain experts’ review, a topic modeling method, Latent Dirichlet allocation (LDA), was used to propose an automatic recommendation system. We also applied prescriptive analytics with an option for users to select appropriate recommendation process of items. Our findings are as follows. First, LDA was efficient to facilitate the analysis of a large collection of documents by decreasing the dimension of the data. Second, the automatic recommendation method with various selectable options that could overcome limitations from that domain experts review the entire set of numerous topics. Finally, as a result of investigation of the final convergence technology candidates, it was proved that the system we propose here is more cost/time-effective compared to a method of reviewing all of the topic associations. Overall, a new methodology to support experts’ final decision by LDAand prescriptive analytics-based automatic recommendation system was successfully developed to discover convergence technologies between BT and ICT, which was also proved by several examples of applications.

Popular music, digital technologies and data analysis: New methods and questions

This article explores how respondents to The Harkive Project ( www.harkive.org ) are enfolding streaming services and automated recommendation systems into their everyday music reception practices. Harkive is an online project running annually on a single day in July that invites people to provide detail and reflection on their experiences with music. Since the project first ran in 2013, it has gathered over 10,000 individual entries. It is conceived as an ongoing experiment in research methodology that attempts to produce an online social space that encourages reflection from respondents about the detail of their music reception practice, while simultaneously acting as a place able to replicate commercial practices around data collection and analysis. This article will demonstrate how such a research process can produce rich descriptive data from respondents who provide a useful snapshot of contemporary music reception practice. The article begins with an overview of how streaming services, data collection from numerous online channels and automated recommendation systems interrelate, and how together they raise questions around how people engage in acts of music reception. It then describes how Harkive is based on similar types of computational/algorithmic processing to those used by key players in the digital music space. The analysis that follows shows that although respondents are engaging in everyday use of streaming services and dynamic recommendations, this engagement tends to be spread across a variety of online channels used in differing combinations, and that it is often recommendations from ‘traditional’ routes, such as media outlets (newspapers, radio stations) and users’ own social groups, that feature prominently in respondent descriptions. Indeed, what Nowak (2016) calls the ‘affective’ element of recommendation appears to be rooted in existing practices that are still in the process of being transposed to the relatively recently emerged digital platforms, rather than – and sometimes in spite of – the rhetorical framing of those platforms as key sites for recommendation and discovery by the companies who operate them. Through a discussion of those findings, and based on an update of Michael Bull’s concept of ‘auditory nostalgia’ (2009), it is then suggested that examining how listeners are enfolding the new technologies of music reception into their everyday routines and routes to meaning-making may be a useful direction for future research. The article then suggests that a mode of working where scholars attempt to reflexively harness data-derived processes may be useful in producing that work, and that experimental and practice-led approaches could enable popular music scholars and listeners alike to develop better epistemic responses to the data-related technologies that have recently helped bring about such huge changes in our everyday music reception practice.

An Automated Recommender System for Educational Institute in India

This study aims to suggest a recommender System for undergraduate students who desire to seek admission into engineering courses in different Indian Institute of Technology (IITs) in India. Initially, the focus is to purpose a recommender system for admission into the top 10 IIT on a pilot basis in four common branches such as Electrical Engineering, Computer Science and Engineering, Mechanical Engineering, Civil Engineering. Data were collected from different authentic sources from 2016 to 2018. A model was built to predict the ranks for 2019 for each branch of every IITs. This paper illustrates prediction using Time Series Forecasting and recommendation algorithm using classification techniques. A comparative study of Random Forest Classification and K-Nearest Neighbor classification has been done. Finally, the recommendation algorithm shown reliable results with high accuracy in prediction model. It can be diversify and implement other streams as part of future work.

Influencing Factors OTA Hotel Online Comments Usefulness-Based on Research of Text Analysis

Based on the OTA hotel online reviews as the research object,using the data mining and Text analysis technology to the empirical analysis of the factors that affect online comments usefulness,and building OTA hotel online comments usefulness influence factors model,and application in China in 2015 various types of OTA online hotel original comments validated data analysis,the results show that the comment of timeliness,score,comments of the emotional negative reviews and comments of the length of online reviews useful have a significant impact,and commnets on the number of positive reviews and comments in a emotional had no significant effect of online comments usefulness.For the comments readers for the automated recommendation systems provides the beneficial enlightenment

Recommendation system with Automated Web Usage data mining using K-Nearest Neighbor(KNN) classification

The major problem of many on-line web sites is the presentation of many choices to the various clients at a time. This usually results into time consumingtask in finding outthe right product or information on the site. The user’s current interest depends upon the navigational behavior which helps the organizations to guideusers in their browsing activities and obtain some relevant information in a short span of time. Since, the resulting patterns which are obtained through data mining techniques did not perform well in the prediction of future browsing patterns because of the low matching rate of resulting rules and of user’s browsing behavior. This paper focuses on the study of the automatic web usage data mining and recommendation system which is based on current user behavior through his/her click stream data. The K-Nearest-Neighbor (KNN) classification method has been trained to be used in real-time and on-line to identify clients and visitors click stream data, matching it to a particular user group and recommends a tailored browsing option that meet the needs of the specific user at particular time.

Time aware topic based recommender system

News recommender systems efficiently handle the overwhelming number of news articles, simplify navigations, and retrieve relevant information. Many conventional news recommender systems use collaborative filtering to make recommendations based on the behavior of users in the system. In this approach, the introduction of new users or new items can cause the cold start problem, as there will be insufficient data on these new entries for the collaborative filtering to draw any inferences for new users or items. Contentbased news recommender systems emerged to address the cold start problem. However, many content-based news recommender systems consider documents as a bag-of-words neglecting the hidden themes of the news articles. In this paper, we propose a news recommender system leveraging topic models and time spent on each article. We build an automated recommender system that is able to filter news articles and make recommendations based on users' preferences. We use topic models to identify the thematic structure of the corpus. These themes are incorporated into a content-based recommender system to filter news articles that contain themes that are of less interest to users and to recommend articles that are thematically similar to users' preferences. Our experimental studies show that utilizing topic modeling and spent time on a single article can outperform the state of the arts recommendation techniques. The resulting recommender system based on the proposed method is currently operational at The Globe and Mail (http://www.theglobeandmail.com/).

Predicting user behavior in electronic markets based on personality-mining in large online social networks

Determining a user’s preferences is an important condition for effectively operating automatic recommendation systems. Since personality theory claims that a user’s personality substantially influences preference, I propose a personality-based product recommender (PBPR) framework to analyze social media data in order to predict a user’s personality and to subsequently derive its personality-based product preferences. The PBRS framework will be evaluated as an IT-artefact with a unique online social network XING dataset and a unique coffeemaker preference dataset. My evaluation results show (a) the possibility of predicting a user’s personality from social media data, as I reached a predictive gain between 23.2 and 41.8 percent and (b) the possibility of recommending products based on a user’s personality, as I reached a predictive gain of 45.1 percent.

Study of Recommendation System for Yoga and Raga for Personalized Health based on Constitution (Prakriti)

nowadays globalization has increased beyond its growth, many challenges and stressful situations need to be faced by human. In Current scenario Ayurveda experts diagnose the diseases by interacting with patients and by examining the patient. They suggest medicine, yoga, raga, and diet according to their observations. Such process is very time consuming. Designing automatic recommendation systems which recommend the yoga and raga for specific prakriti.it will help experts to reduce certain amount of time, such system recommend accurate yoga and raga according to physical and mental characteristics of person (Prakriti).Neural Network Technology and decision tree will be used to design recommendation system for generating rules based on Constitution, Timing, Atmosphere, Mood, and Disorder. KeywordsNetwork, Decision Tree, Prakriti, Raga, Yoga.

An Automated Recommender System for Course Selection

Most of electronic commerce and knowledge management` systems use recommender systems as the underling tools for identifying a set of items that will be of interest to a certain user. Collaborative recommender systems recommend items based on similarities and dissimilarities among users’ preferences. This paper presents a collaborative recommender system that recommends university elective courses to students by exploiting courses that other similar students had taken. The proposed system employs an association rules mining algorithm as an underlying technique to discover patterns between courses. Experiments were conducted with real datasets to assess the overall performance of the proposed approach.

Curation by code: Infomediaries and the data mining of taste

Automated recommendation systems now occupy a central position in the circulation of media and cultural products. Using music as a test case, this article examines the use of algorithms and data mining techniques for the presentation and representation of culture, and how these tools reconfigure the process of cultural intermediation. Expanding Bourdieu’s notion of cultural intermediaries to include technologies like algorithms, I argue that an emerging layer of companies – call them infomediaries – are increasingly responsible for shaping how audiences encounter and experience cultural content. Through a critical analysis of The Echo Nest, a music infomediary whose databases underpin many digital music services, I trace the shift from intermediation to infomediation and explore what is at stake at the intersection of data mining, taste making and audience manufacture. The new infomediary logics at work are computational forms of power that shape popular culture and highlight the social implications of curation by code.

A New Approach for Mining Order-Preserving Submatrices Based on All Common Subsequences.

Order-preserving submatrices (OPSMs) have been applied in many fields, such as DNA microarray data analysis, automatic recommendation systems, and target marketing systems, as an important unsupervised learning model. Unfortunately, most existing methods are heuristic algorithms which are unable to reveal OPSMs entirely in NP-complete problem. In particular, deep OPSMs, corresponding to long patterns with few supporting sequences, incur explosive computational costs and are completely pruned by most popular methods. In this paper, we propose an exact method to discover all OPSMs based on frequent sequential pattern mining. First, an existing algorithm was adjusted to disclose all common subsequence (ACS) between every two row sequences, and therefore all deep OPSMs will not be missed. Then, an improved data structure for prefix tree was used to store and traverse ACS, and Apriori principle was employed to efficiently mine the frequent sequential pattern. Finally, experiments were implemented on gene and synthetic datasets. Results demonstrated the effectiveness and efficiency of this method.

Codebook-Based Audio Feature Representation for Music Information Retrieval

Digital music has become prolific in the web in recent decades. Automated recommendation systems are essential for users to discover music they love and for artists to reach appropriate audience. When manual annotations and user preference data is lacking (e.g. for new artists) these systems must rely on content based methods. Besides powerful machine learning tools for classification and retrieval, a key component for successful recommendation is the audio content representation. Good representations should capture informative musical patterns in the audio signal of songs. These representations should be concise, to enable efficient (low storage, easy indexing, fast search) management of huge music repositories, and should also be easy and fast to compute, to enable real-time interaction with a user supplying new songs to the system. Before designing new audio features, we explore the usage of traditional local features, while adding a stage of encoding with a pre-computed codebook and a stage of pooling to get compact vectorial representations. We experiment with different encoding methods, namely the LASSO, vector quantization (VQ) and cosine similarity (CS). We evaluate the representations' quality in two music information retrieval applications: query-by-tag and query-by-example. Our results show that concise representations can be used for successful performance in both applications. We recommend using top- τ VQ encoding, which consistently performs well in both applications, and requires much less computation time than the LASSO.

Automatic stress-relieving music recommendation system based on photoplethysmography-derived heart rate variability analysis.

This paper presents an automatic stress-relieving music recommendation system (ASMRS) for individual music listeners. The ASMRS uses a portable, wireless photoplethysmography module with a finger-type sensor, and a program that translates heartbeat signals from the sensor to the stress index. The sympathovagal balance index (SVI) was calculated from heart rate variability to assess the user's stress levels while listening to music. Twenty-two healthy volunteers participated in the experiment. The results have shown that the participants' SVI values are highly correlated with their prespecified music preferences. The sensitivity and specificity of the favorable music classification also improved as the number of music repetitions increased to 20 times. Based on the SVI values, the system automatically recommends favorable music lists to relieve stress for individuals.

Study on Directed Trust Graph Based Recommendation for E-commerce System

Automated recommender systems have played a more and more important role in marketing and ever increasingly booming e-commerce systems. They provide useful predictions personalized recommendations according to customers’ characteristics and a variety of large and complex product offerings. In many of these recommendation technologies C ollaborative Filtering (CF) has proven to be one of the most successful recommendation method, which has been widely used in many e-commerce systems. The success of CF recommendation depends mainly on locating similar neighbors to get recommendation items. However, many scholars have found that the process of finding similar neighbors often fail, due to some inherent weaknesses of CF based recommendation. In view of this, we propose a trust feedback recommendation algorithm based on directed trust graph (DTG), which is able to propagate trust relationship. In our approach, there is no need to compute similarity between users, but utilize the trust relation between them to conduct prediction calculation. Based on the analysis of human trust perception, we incorporate the process into our recommendation algorithm. Experimental evaluation on r eal life Epinions datasets shows that the effectiveness and practicability of our approach.

Predicting Quality of Answer in Collaborative Question Answer Learning

Studies over the years shown that students had actively and more interactively involved in a classroom discussion to gain their knowledge. By posting questions for other participants to answer, students could obtain several answers to their question. The problem is sometimes the answer chosen by student as the best answer is not necessarily the best quality answer. Therefore, an automatic recommender system based on student activity, may improve these situations as it will choose the best answer objectively. On the other side, in the implementation of collaborative learning, in addition to sharing information, sometimes students also need a reference or domain knowledge which relevant with the topic. In this paper, we proposed answer quality predictor in collaborative question answer (CQA) learning, to predict the quality of answer either from recommender system based on users activity or domain knowledge as reference information.

A Fuzzy Based Approach for Student Admission Recommendation into Seminary

Education is a complex systematic engineering, which is the guarantee of training high-quality talent, helping society make full use of educational outcomes and promote the healthy development of education. To step-in to that high quality education students have a chaos in evaluating the best among the several institutions and select the one. In this paper, we suggest an automatic student admission recommendation system that selects a set of institutions by considering a set of student prerequisites and semantically match them with their parameters. Fuzzy clustering technique is applied on categorized data for suggesting better suited colleges for a particular student based on his/her course option. Since the same student can opt for more than one college for a particular course, depending upon multiple parameters, fuzzy clustering acts as the best suited method for seminary recommendation. The relative fuzzy score called “degree of membership” calculated for each college indicates the membership of a particular student to different institutions. Subjective evaluation of the algorithm is tested on synthetic dataset and the experiments produce promising results. Keywords: Synthetic dataset, Fuzzy sets, Clustering, Text Categorization, Smart selection