Clinical decision-making is complex and time-intensive. To help in this effort, clinical recommender systems (RS) have been designed to facilitate healthcare practitioners with personalized advice. However, designing an effective clinical RS poses challenges due to the multifaceted nature of clinical data and the demand for tailored recommendations. In this article, we introduce a 2-Stage Recommendation framework for clinical decision-making, which leverages a publicly accessible dataset of electronic health records. In the first stage, a deep neural network-based model is employed to extract a set of candidate items, such as diagnoses, medications, and prescriptions, from a patient's electronic health records. Subsequently, the second stage utilizes a deep learning model to rank and pinpoint the most relevant items for healthcare providers. Both retriever and ranker are based on pre-trained transformer models that are stacked together as a pipeline. To validate our model, we compared its performance against several baseline models using different evaluation metrics. The results reveal that our proposed model attains a performance gain of approximately 12.3% macro-average F1 compared to the second best performing baseline. Qualitative analysis across various dimensions also confirms the model's high performance. Furthermore, we discuss challenges like data availability, privacy concerns, and shed light on future exploration in this domain.

The prominence of social media poses a significant threat to information integrity as the spread of fake news increases. It becomes imperative for online media outlets to develop effective strategies to mitigate the spread of fake news. In this research, the PLNCC dataset is introduced as an expansion of two state-of-the-art fake news datasets. The objective is to improve the classification of fake news by extracting additional linguistic and psychological features, as well as user comment data. In this work, a quantitative analysis of the linguistic and psychological features of fake news articles and related user comments is performed. The efficacy of the PLNCC dataset is demonstrated through rigorous evaluation, showcasing its performance against state-of-the-art benchmark datasets. The classification models running on this dataset achieved a significant performance improvement, up to 10%, when compared to the original two datasets.

In this paper, we offer a new visualization tool -- Dataset Statistical View (DSV), to lower the barrier of research entry by providing easy access to the question-answering (QA) datasets that researchers can build their work upon. Our target users are new researchers to the QA domain with no prior knowledge nor programming skills. The system is populated with multiple QA datasets, which covers a wide range of QA tasks. It allows researchers to explore and compare existing QA datasets at a one-stop website. The system shows statistical graphs for each QA dataset to offer an overview and a visual comparison between datasets. Although this paper focuses mainly at the syntactic level comparison, integrating bias and semantic level analysis is our ongoing work. We believe our DSV system is a valuable contribution to the advancement of the QA field, as it provides a solid starting point for new researchers and practitioners. An overview of the framework is demonstrated in this paper and the introduction of the application system is available at https://cnchuy.github.io/images/demo.mp4.

These days, due to the advancement of information technology, recommendation system has become one of the key tools for e-commerce business. E-commerce platforms allow users to provide feedback in both written comments and numerical ratings. Recommendation systems are utilized to recommend users to new or unseen items based on these previously collected comments or ratings. In recent years, multi-aspect or multi-criteria based recommendation systems have been studied a lot by the recommendation research community. However, these research works are conducted either with reviews or ratings, not with both. In this project, we argue that integrating both textual reviews (with multiple aspects) and numerical multi-criteria ratings can further enhance the overall rating prediction accuracy. We propose a Multi-criteria Rating and Review based Recommendation model (MRRRec). We show that incorporating multi-criteria ratings into multi-aspect ratings from reviews has a great impact on performance. Our proposed model outperforms several state-of-the-art models such as ANR, DeepCoNN, and Deep Multi-criteria Recommendation System in terms of MSE, MAE, precision, recall, and F1. We show that our proposed model achieves an average of 19% and 23.0% lower MSE and MAE respectively and 7.0%, 1.0% and 3.8% higher precision, recall, and F1 score respectively. We further show that our model performs significantly better with Word2Vec word embedding than the GloVe word embedding method.

The news recommender systems are marked by a few unique challenges specific to the news domain. These challenges emerge from rapidly evolving readers’ interests over dynamically generated news items that continuously change over time. News reading is driven by a blend of a reader’s long-term and short-term interests. In addition, diversity is required in a news recommender system to keep the reader engaged in the reading process and get them exposed to different views and opinions. This paper proposes a deep neural network that jointly learns news and user representation in a unified framework. It learns the news representation (features) from the headlines, snippets (body) and taxonomy (category, subcategory) of news. The attention mechanism learns a reader’s long-term interests from the complete click history, short-term interests from recent clicks via LSTMs and diverse interests. We also apply different levels of attention to our model. We conduct extensive experiments on two news datasets to demonstrate the effectiveness of our approach.

The user feedback data such as likes, dislikes, comments on movie trailers posted on YouTube can be a useful information source for movie recommender systems. In this paper, we study the effect of adding the feedback data on trailers as a type of the side information to the movie rating data. We propose a recommendation framework that can integrate the trailer and rating data adopting different integration strategies: integrating all the trailer data as movie features, using sentiment scores derived from the trailer comments as a rating matrix to integrate with the movie rating matrix and treating others as the movie features, or only integrating the sentiment score based rating matrix with the movie rating matrix. Our experiment shows that if we include the movie trailer data, recommendation accuracy is improved. We also find that the most accurate result is achieved if all the trailer feedback data is integrated as movie features. To design our system, we use both Matrix Factorization (MF) and Deep Neural Network (DNN) Models. We find that the DNN model performs better than the MF model.

News recommender systems are usually designed to provide accurate and personalized recommendations to the readers. The diversity of the recommended results has received much less attention in this field. When it is considered, the current state-of-the-art models often apply the re-ranking mechanisms to promote the diversified results to the individual users. In this work, we propose a latent factor model to achieve the requisite level of accuracy while maintaining a reasonable level of diversity in a news recommender system. The existing latent factor methods mostly rely on Tikhonov regularization to improve the generality of the learnt models. These methods tend to focus mainly on accuracy measures, i.e., generating recommendations highly aligned with a user's past preference, which may cause a decrease in the diversity of information to which news readers are exposed. In our work, we make effective use of elastic-net regression to regularize the model for both the accuracy and the diversity in a single optimization framework. We demonstrate the effectiveness of our model over the state-of-the-art methods by conducting extensive experiments on a real-world news dataset.

In the past, news recommender systems have been built to recommend list of news items similar to those that a user has accessed before (content-based); or similar to those that have been read by similar users (collaborative filtering). However, the highly volatile nature of the news content and the dynamic and evolving user preferences are either ignored or not taken into full consideration in these systems. In a news recommender system, it is very likely that a user's short-term interest or preference may have a sudden change due to an emerging social or personal event or breaking news while their long-term interests may change gradually or remain. For these long-term interests of the readers, it is often more appropriate to associate them with news categories than with individual news items. In this paper, we propose a biased matrix factorization model with consideration of both temporal dynamics of user preferences and news taxonomy to build a news recommender system. By conducting an extensive experiment on a collection of news data, we demonstrate the effectiveness of our proposed model against traditional matrix factorization models as well as other neural recommender baselines. The findings from our experiments show that news category is an important factor when readers choose news articles to read, and temporal factors with consideration of different temporal resolution also play a role in this process.

Most of the current research work on web service selection has only considered the selection problem from the perspective of one party - service users. The selection model usually tries to find services which can optimize the user requirements. However, a service marketplace serves multiple parties, including both service users and providers. Thus, it is important to consider multiple parties when selecting services in a marketplace. In this paper, we propose a service selection algorithm considering the benefits of multiple parties: users, providers and the marketplace itself. The algorithm ranks services based on not only how much these services satisfy the user requirements but also how much the requests can be distributed to different providers and how much profit the marketplace can gain. The experimental results on a simulated dataset show that the proposed model could achieve a high degree of satisfaction of user requests, and meanwhile have the capability of promoting more diversified set of services.

With the fast increase of online services of all kinds, users start to care more about the Quality of Service (QoS) that a service provider can offer besides the functionalities of the services. As a result, QoS-based service selection and recommendation have received significant attention since the mid-2000s. However, existing approaches primarily consider a small number of standard QoS parameters, most of which relate to the response time, fee, availability of services, and so on. As online services start to diversify significantly over different domains, these small set of QoS parameters will not be able to capture the different quality aspects that users truly care about over different domains. Most existing approaches for QoS data collection depend on the information from service providers, which are sensitive to the trustworthiness of the providers. Some service monitoring mechanisms collect QoS data through actual service invocations but may be affected by actual hardware/software configurations. In either case, domain-specific QoS data that capture what users truly care about have not been successfully collected or analyzed by existing works in service computing. To address this demanding issue, we develop a statistical learning approach to extract domain-specific QoS features from user-provided service reviews. In particular, we aim to classify user reviews based on their sentiment orientations into either a positive or negative category. Meanwhile, statistical feature selection is performed to identify statistically nontrivial terms from review text, which can serve as candidate QoS features. We also develop a topic models-based approach that automatically groups relevant terms and returns the term groups to users, where each term group corresponds to one high-level quality aspect of services. We have conducted extensive experiments on three real-world datasets to demonstrates the effectiveness of our approach.

QoS-based service selection has been an active research area in both Service Computing and Cloud Computing communities in recent years. One of the obstacles for many researchers is lack of benchmark QoS datasets, especially for cloud service selection. In this paper, we propose a testbed system which can be used to collect the QoS data for software services hosted in the cloud. We mainly focus on analytic services, whose QoS values could be dependent on the data they are used to process and analyze. Using the testbed, we can publish services (software or infrastructure services), we can invoke software services hosted on certain infrastructure services, and system can monitor and record the QoS values of all the invocations. We have implemented a proof-of-concept prototype system and used it to collect a sample QoS dataset.

Social network is a hot topic of interest for the researchers in the field of computer science in recent years. The vast amount of data generated by these social networks play a very important role in information diffusion. Social network data are generated by its users. So, user's behavior and activities are being investigated by the researchers to get a logical view of social network platform. This research proposed a novel retweet prediction model which considers difference in user's behavior as an author (as reflected in the tweets) and a retweeter (as reflected in the retweets) and do the prediction accordingly. The proposed retweet prediction strategy taking this difference into consideration, gave better prediction accuracy than the conventional strategy. The findings of this research explains that in social networks, some users show different behavior indifferent roles and these differences may have impact on future research.

Classifying Web services and labeling them based on their functional features have played a major role in several fundamental service management tasks, such as service discovery, selection, ranking, and recommendation. Existing approaches leverage text mining techniques and follow a supervised learning process, which involves building a classifier from a training set of services and applying the classifier to other services. This process requires intensive human effort on labeling services in the training set. In this paper, we propose to leverage the idea of pool-based active learning to realize a scalable service classification approach. Instead of manually labeling a large number of services to construct a complete training set, the approach starts with a base classifier with a small set of training set and iteratively asks for the labels of the most informative services outside of the initial training set. By doing this, the classifier can achieve comparable accuracy compared to traditional classification method with much smaller size of training set. We use SVM as the base classifier due to its effectiveness in text classification. We also incorporate probabilistic topic models to address the issues caused by sparse term vectors generated from service descriptions and reduce the dimensions to improve the efficiency. We conducted a comprehensive experimental study on real-world service data to demonstrate the effectiveness of the proposed approach.

In a cloud-based service selection system, for a given request, there could be a large number of software services matching the functional requirements. The selection should then be done based on their QoS values. Since in a cloud environment, a software service might need collaboration from other types of cloud services (e.g., A software service delivered through an infrastructure service) to offer a complete solution to an end user, the selection system should have a way to measure the QoS values of the whole solution, instead of QoS of software services alone. This kind of end-to-end QoS values of cloud-based software solutions may or may not be available in recorded history logs. In this paper, we propose a model for predicting end-to-end QoS values of cloud-based software solutions composed of services from multiple cloud layers. It relies on the internal features of services and end users such as locations, configurations, functionality, and user profiles to calculate service similarity and then predict QoS values. The experiments demonstrate the accuracy of our approach. We also studied the impact of the proposed internal features on QoS prediction accuracy.

Cloud computing is an attractive platform which offers on-demand resources as services. When many cloud services are available, some may have similar or same functionalities. So cloud service recommendation, which can help users to select the services based on their preferences, become an important technique for cloud services. In this paper, we review the relevant technologies that can perform cloud service recommendation. First, we introduce the web service selection and recommendation technologies. Next, we describe QoS measurement for cloud service and different recommendation methods focusing on Collaborative filtering. Third, we discuss the research challenges and opportunities for cloud service recommendation.

Quality of Service (QoS) has become a standard way of evaluating web services and selecting the one that suites user interests the best. Traditional methods adopt a fixed set of QoS parameters and typical ones include response time, fee, and availability. There currently lacks an effective way of identifying quality features that users are actually interested in when choosing a service. Meanwhile, the traditional way of collecting QoS values relies on either public information released by service providers or test results from repeatedly invoking a service. Therefore, the values can be heavily affected by authenticity of the provider offered information or the quality/configuration of the test code/environment. As a result, existing QoS evaluation methods are not applicable to subject features, such as usability and affordability, where the values depend on user personal judgement. In this paper, we propose a novel approach to extracting domain-related QoS features, ranking those features based on their interestingness, evaluating the value of these features through sentiment analysis on user reviews. More specifically, we leverage natural language processing techniques and machine learning approaches to identify top QoS features that users are interested in and simultaneously learn their sentiment orientation towards those features. We model the problem as sentiment classification, where relevant terms in a review are modeled as features that determine whether a review is positive or negative. Logistic regression is used so that the impact of these terms are learned simultaneously when the classifier is learned through a supervised learning process. The nontrivial terms are selected as the candidate QoS featured. A comprehensive experiment has been conducted on a real-world dataset and the result demonstrates the effectiveness of our approach.

In order to choose from a list of functionally similar services, users often need to make their decisions based on multiple QoS criteria they require on the target service. In this process, different users may follow different decision making strategies, some are compensatory in which only an overall value on all the criteria is evaluated, some evaluate one criterion at a time in the order of their importance levels, while others count on the number of winning criteria. Most of the current QoS-based service selection systems do not consider these decision strategies in the ranking process, which we believe are crucial for generating accurate ranking results for individual users. In this paper, we propose a decision strategy based service ranking model. Furthermore, considering that different users follow different strategies in different contexts at different times, we apply a machine learning algorithm to learn a personalized ranking model for individual users based on how they select services in the past. We have implemented and tested the proposed approach, and our experiment results show the effectiveness of the approach.

In order to choose from a list of functionally similar services, users often need to make their decisions based on multiple QoS criteria they require on the target service. In this process, different users may follow different decision making strategies, some are compensatory in which only an overall value on all the criteria is evaluated, some evaluate one criterion at a time in the order of their importance levels, while others count on the number of winning criteria. Most of the current QoS-based service selection systems do not consider these decision strategies in the ranking process, which we believe are crucial for generating accurate ranking results for individual users. In this paper, we propose a decision strategy based service ranking model. Furthermore, considering that different users follow different strategies in different contexts at different times, we apply a machine learning algorithm to learn a personalized ranking model for individual users based on how they select services in the past. Our experiment result shows the effectiveness of the proposed approach.

Recently, researchers have taken tremendous strides in attempting to synthesize conventional social judgments and automated filtering within recommender systems. In this study, we aim to enhance recommendation efficiency via integrating social networking information with traditional recommendation algorithms. To achieve this objective, we first propose a new user similarity metric that not only considers tagging activities of users, but also incorporates their social relationships, such as friendship and membership, in measuring the closeness of two users. Subsequently, we define a new item prediction method which makes use of both user-to-user similarity and item-to-item similarity. Experimental outcomes on Last.fm show some positive results that attest the efficiency of our proposed approach.

We propose a novel approach to discover workflow models from event logs. The proposed approach addresses two major limitations of current process mining approaches. First, they assume either a single workflow model for the entire event log or the availability of workflow ids that can be used to group logs associated with the same workflow model together. Nonetheless, these assumptions are oversimplified as a complex system typically runs multiple workflow models, all of which share the same log system. Second, existing process mining approaches do not consider the usage patterns of workflow users. Most systems support multi-users and each user is typically associated with (or use) certain number of operation sequences, which may all follow one or several workflow models. Hence, we propose to leverage User Behavior Patterns (or UBPs) to improve the outcome of process mining. In particular, we exploit machine learning techniques to incorporate UBPs into sequence clustering for workflow model discovery. We model a UBP as a probabilistic distribution on sequences, which allows to compute the distance between a UBP and any sequence. We apply three-way matrix factorization onto a UBP-sequence distance matrix to co-cluster users and sequences. In this way, users that share similar UBPs are grouped together while the clustering of similar sequences will lead to the discovery of workflow models. An comprehensive experimental study is conducted to demonstrate the effectiveness and efficiency of the proposed approach.

Non-Functional (NF) requirement is very important for the success of a software service. Considering that there could be multiple services implementing a same function, it is crucial for software providers to understand the real NF demands from consumers so that they can meet these demands and attract users. It is also crucial for consumers to know what is being offered so that they can pose realistic NF requests. We address both issues here by proposing a NF requirement analysis and recommendation system which works for both providers and consumers. NF requirements from various sources are first collected, and then we apply the factor analysis technique to identify those independent latent factors which contribute to those observable NF values. Finally we use cluster analysis to summarize the popular NF demands. Our experiment result shows the effectiveness of this approach.

In order to select and rank the best services in a cloud computing environment, the end-to-end quality of service (QoS) values of cloud services have to be computed. For a new SaaS provider, the deployment of its software application in the cloud is a challenging job. It has to find a hosting service (IaaS) that hosts its service. The primary goal of the SaaS provider is to make its service at the top of the ranked list of cloud services returned to end users through satisfying their QoS requirements. In this paper, we propose a mechanism to map the users' QoS requirements of cloud services to the right QoS specifications of SaaS then map them to best IaaS service that offers the optimal QoS guarantees. Then together SaaS and IaaS services can provide the best service offer to end users. As a result of the mapping, the end-to-end QoS values can be calculated. We propose a set of rules to perform the mapping process. We hierarchically model the QoS specifications of cloud services using the Analytic Hierarchy Process (AHP) method. The AHP based model helps to facilitate the mapping process across the cloud layers, and to rank the candidate cloud services for end users. We use a case study to illustrate and validate our solution approach.

Many QoS-based service selection algorithms are complex and time-consuming, and sometimes require a lot of manual efforts from users. As a result, users' real-time searching experiences may not be good when there are many candidate services, because it could be very slow to calculate the ranking scores of services. In this paper, we want to improve the efficiency of the selection process by using a simple vector space model. We also consider the actual QoS requirements from users in the ranking process, which is missing in many current systems. Our experiment results show a big improvement on the system efficiency without losing much on the accuracy when compared with a well-known algorithm -- skyline computation.

Collaborative filtering based recommender systems are very successful on dealing with the information overload problem and providing personalized recommendations to users. When more and more web services are published online, this technique can also help recommend and select services which satisfy users' particular Quality of Service (QoS) requirements and preferences. In this paper, we propose a novel collaborative filtering based service ranking mechanism, in which the invocation and query histories are used to infer the user behavior, and user similarity is calculated based on similar invocations and queries. To overcome some of the inherent problems with the collaborative filtering systems such as the cold start and data sparsity problem, the final ranking score is a combination of the QoS-based matching score and the collaborative filtering based score. The experiment using a simulated dataset proves the effectiveness of the algorithm.

In this paper, we investigate selection strategies for rescue servers in a fully collaborative in which heterogeneous systems share spare resource to address hotspot problems experienced by individual members. Different from content replication, delays due to application replication and startup time of the resulting rescue servers will be taken into consideration. Details about our replication strategy, such as the maximum set size margin on the total number of discarded requests, overall latency for enabling rescue servers, are given. Simulation result shows that our selection strategies perform much better than existing mechanisms in which replication and startup delay are ignored.

In this paper, we propose an adaptive quality recommendation mechanism to help software service providers understand the dynamism of quality demand from the majority of requesters accurately. The unique feature of our approach is that based on the intra-cluster proximity index (called the icp-index) that we propose, the granularity of service clustering can be adjusted dynamically to meet the wide variation of service providers who want to target their services to different groups of clients. Experiments show that our approach is more accurate and flexible to identify the need of service quality of requesters than existing solutions such as simple averaging, minimum-maximum-mean, or traditional interval-range data clustering.

Normally, the unit for a ranking model in a Web IR system is a Web page, which is, sometimes, just an information fragment. A larger unit considering the linkage information may be desired to reduce the cognitive overload for users to identify the complete information from the interconnected Web. We propose a ranking model to measure the relevance of the whole Web site. We take some illustrations to show the idea and provide evidences to indicate its effectiveness.

There is an important query requirement missing for search engines. With the wide variation of domain knowledge and user interest, a user would like to retrieve documents in which one query term is discussed in the context of another. Based on existing query mechanisms, what can be specified at most is the co-occurrence of multiple terms in a query. This is insufficient because the co-occurrence of two terms does not necessarily mean that one is discussed in the context of the other. In this paper we propose the context query for Web searching. A new query operator, called the 'in' operator, is used to specify context inclusion between two terms. Heuristic rules to identify context inclusion are suggested and implementation of the 'in' operator in search engines is proposed. Results show that both the precision and ranking relevance of Web searching are improved significantly.

The relevance of a Web document could be measured not only by its text content, but also by some other factors such as the link connectivity and usage patterns. In previous data fusion researches, the text is the only source to determine the relevance, and only the different runs (e.g. by different retrieval models, different query or document representations) on this same source are combined. It is the purpose of this paper to investigate whether the different sources can be combined to determine the relevance with a better accuracy than any single source. We conducted a preliminary experiment to test its feasibility and effectiveness and a positive result was obtained.

Due to the lack of back-pointers, information about the referral parent(s) of a given Web page is not usually available to Web surfers. This significantly reduces the effectiveness of Web surfing and information discovery. We propose a mechanism to locate the referral parent(s) for a given fragment of a Web document (in terms of an URL address) from the client side. The basic idea is to explore the hierarchical hyperlink structure of a Web document fragment from its storage path directory information that is embedded in its URL. Two mechanisms were proposed: exhaustibility first search (EFS) and generalization first search (GFS). Results showed that through direct mapping of the storage hierarchy path to the URL address and then performing reverse tracing along the hyperlink structure, the chance of discovering a referral parent ranged from 41% to 51%. Compared to EFS, GFS was found to reduce the average search space from 26 pages to 4 pages.

No abstract available.

No abstract available.

It is observed that a better approach to Web information understanding is to base on its document framework, which is mainly consisted of (i) the title and the URL name of the page, (ii) the titles and the URL names of the Web pages that it points to, (iii) the alternative information source for the embedded Web objects, and (iv) its linkage to other Web pages of the same document. Investigation reveals that a high percentage of words inside the document framework are “compound words” which cannot be understood by ordinary dictionaries. They might be abbreviations or acronyms, or concatenations of several (partial) words. To recover the content hierarchy of Web documents, we propose a new word segmentation and recognition mechanism to understand the information derived from the Web document framework. A maximal bi-directional matching algorithm with heuristic rules is used to resolve ambiguous segmentation and meaning in compound words. An adaptive training process is further employed to build a dictionary of recognisable abbreviations and acronyms. Empirical results show that over 75% of the compound words found in the Web document framework can be understood by our mechanism. With the training process, the success rate of recognising compound words can be increased to about 90%.