scholarly journals A Multitask Learning Model with Multiperspective Attention and Its Application in Recommendation

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Yingshuai Wang ◽  
Dezheng Zhang ◽  
Aziguli Wulamu
Keyword(s):  
User Satisfaction ◽  
Multitask Learning ◽  
Attention And Memory ◽  
User Interest ◽  
Training Models ◽  
User Interests ◽  
Interaction Mode ◽  
Public Data ◽  
Fusion Mode ◽  
Different Characteristics

Training models to predict click and order targets at the same time. For better user satisfaction and business effectiveness, multitask learning is one of the most important methods in e-commerce. Some existing researches model user representation based on historical behaviour sequence to capture user interests. It is often the case that user interests may change from their past routines. However, multi-perspective attention has broad horizon, which covers different characteristics of human reasoning, emotions, perception, attention, and memory. In this paper, we attempt to introduce the multi-perspective attention and sequence behaviour into multitask learning. Our proposed method offers better understanding of user interest and decision. To achieve more flexible parameter sharing and maintaining the special feature advantage of each task, we improve the attention mechanism at the view of expert interactive. To the best of our knowledge, we firstly propose the implicit interaction mode, the explicit hard interaction mode, the explicit soft interaction mode, and the data fusion mode in multitask learning. We do experiments on public data and lab medical data. The results show that our model consistently achieves remarkable improvements to the state-of-the-art method.

Discovery and classification of user interests on social media

2017 ◽  
Vol 45 (3) ◽  
pp. 130-138 ◽  
Author(s):  
Basit Shahzad ◽  
Ikramullah Lali ◽  
M. Saqib Nawaz ◽  
Waqar Aslam ◽  
Raza Mustafa ◽  
...  
Keyword(s):  
Information Filtering ◽  
Recommendation Systems ◽  
Personalized Recommendation ◽  
Support Vector ◽  
User Interest ◽  
Socioeconomic Impacts ◽  
Content Type ◽  
Positive Correlation ◽  
User Interests ◽  
Twitter Users

Purpose Twitter users’ generated data, known as tweets, are now not only used for communication and opinion sharing, but they are considered an important source of trendsetting, future prediction, recommendation systems and marketing. Using network features in tweet modeling and applying data mining and deep learning techniques on tweets is gaining more and more interest. Design/methodology/approach In this paper, user interests are discovered from Twitter Trends using a modeling approach that uses network-based text data (tweets). First, the popular trends are collected and stored in separate documents. These data are then pre-processed, followed by their labeling in respective categories. Data are then modeled and user interest for each Trending topic is calculated by considering positive tweets in that trend, average retweet and favorite count. Findings The proposed approach can be used to infer users’ topics of interest on Twitter and to categorize them. Support vector machine can be used for training and validation purposes. Positive tweets can be further analyzed to find user posting patterns. There is a positive correlation between tweets and Google data. Practical implications The results can be used in the development of information filtering and prediction systems, especially in personalized recommendation systems. Social implications Twitter microblogging platform offers content posting and sharing to billions of internet users worldwide. Therefore, this work has significant socioeconomic impacts. Originality/value This study guides on how Twitter network structure features can be exploited in discovering user interests using tweets. Further, positive correlation of Twitter Trends with Google Trends is reported, which validates the correctness of the authors’ approach.

Mining User Interests and Change Patterns in Microblog

2013 ◽  
Vol 380-384 ◽  
pp. 1959-1962
Author(s):  
Dong Liu ◽  
Quan Yuan Wu
Keyword(s):  
Feature Vector ◽  
Hamming Distance ◽  
User Interest ◽  
User Interests ◽  
Series Of Experiments ◽  
Share Information

Nowadays, more and more people use microblogs to share information. Consequently, mining microblog users behavior features is very valuable. In the paper, we propose a user interest mining framework. After data pre-processing, VSM is used to generate the feature vector of the tweet sets. Furthermore, k-bit binaries called interest hash-value and continuous interest hash-value are generated by use of Simhash algorithm. The user interests and change patterns could be mined by analyzing the hamming distance sequences between adjacent two hash-values. Taking Sina microblog as background, a series of experiments are done to prove the effectiveness of the algorithms.

Two Phase Recommendation Algorithm Based on Clustering User Interest and Trust

2014 ◽  
Vol 543-547 ◽  
pp. 1856-1859
Author(s):  
Xiang Cui ◽  
Gui Sheng Yin
Keyword(s):  
Social Networks ◽  
Electronic Commerce ◽  
Recommender Systems ◽  
Information Overload ◽  
User Interest ◽  
Recommendation Algorithm ◽  
Two Phase ◽  
Rating Data ◽  
User Interests ◽  
The Future

Recommender systems have been proven to be valuable means for Web online users to cope with the information overload and have become one of the most powerful and popular tools in electronic commerce. We need a method to solve such as what items to buy, what music to listen, or what news to read. The diversification of user interests and untruthfulness of rating data are the important problems of recommendation. In this article, we propose to use two phase recommendation based on user interest and trust ratings that have been given by actors to items. In the paper, we deal with the uncertain user interests by clustering firstly. In the algorithm, we compute the between-class entropy of any two clusters and get the stable classes. Secondly, we construct trust based social networks, and work out the trust scoring, in the class. At last, we provide some evaluation of the algorithms and propose the more improve ideas in the future.

Sections, categories and keywords as interest specification tools for personalised news services

2001 ◽  
Vol 25 (3) ◽  
pp. 149-160 ◽  
Author(s):  
Alberto Díaz ◽  
Pablo Gervás ◽  
Antonio García ◽  
Inmaculada Chacón
Keyword(s):  
User Satisfaction ◽  
General Information ◽  
Test Cases ◽  
User Interest ◽  
General Applicability ◽  
Digital News ◽  
Actual Evaluation ◽  
Close Study ◽  
News Services ◽  
Evaluation Of System Performance

Through an evaluation of system performance and user satisfaction for the Mercurio system, considers the general applicability and usefulness of different methods of specifying user interest for the general case of digital news services. Outlines the specific characteristics distinguishing such systems from more general information systems and discusses their effect. Proposes an evaluation blueprint for them starting from information retrieval procedures, existing work on search engine evaluation, and a close study of the working principles and the required evaluation according to the particular properties and conditions of the services under consideration. Presents and discusses actual evaluation results for system tests based both on real users and customised test cases. Conclusions cover the nature of the information handling tasks that digital news services are faced with, the relative merits of sections, categories and keywords with respect to this particular set of tasks, and the risks of careless application of recall and precision measures in systems such as these.

scholarly journals Country-Specific Interests towards Fall Detection from 2004–2021: An Open Access Dataset and Research Questions

Data ◽  
2021 ◽  
Vol 6 (8) ◽  
pp. 92
Author(s):  
Nirmalya Thakur ◽  
Chia Y. Han
Keyword(s):  
Public Health ◽  
Open Access ◽  
Data Science ◽  
Fall Detection ◽  
Time Range ◽  
User Interest ◽  
User Interests ◽  
The World ◽  
Research Questions ◽  
Google Search

Falls, which are increasing at an unprecedented rate in the global elderly population, are associated with a multitude of needs such as healthcare, medical, caregiver, and economic, and they are posing various forms of burden on different countries across the world, specifically in the low- and middle-income countries. For these respective countries to anticipate, respond, address, and remedy these diverse needs either by using their existing resources, or by developing new policies and initiatives, or by seeking support from other countries or international organizations dedicated to global public health, the timely identification of these needs and their associated trends is highly necessary. This paper addresses this challenge by presenting a study that uses the potential of the modern Internet of Everything lifestyle, where relevant Google Search data originating from different geographic regions can be interpreted to understand the underlining region-specific user interests towards a specific topic, which further demonstrates the public health need towards the same. The scientific contributions of this study are two-fold. First, it presents an open-access dataset that consists of the user interests towards fall detection for all the 193 countries of the world studied from 2004–2021. In the dataset, the user interest data is available for each month for all these countries in this time range. Second, based on the analysis of potential and emerging research directions in the interrelated fields of Big Data, Data Mining, Information Retrieval, Natural Language Processing, Data Science, and Pattern Recognition, in the context of fall detection research, this paper presents 22 research questions that may be studied, evaluated, and investigated by researchers using this dataset.

Evaluation of Literature Reading Value Based on User Interests Mining

2014 ◽  
Vol 513-517 ◽  
pp. 2068-2072
Author(s):  
Ya Hui Zhao ◽  
Zhen Guo Zhang ◽  
Rong Yi Cui
Keyword(s):  
Evaluation Method ◽  
Comprehensive Evaluation ◽  
Evaluation Model ◽  
Feature Space ◽  
Semantic Space ◽  
Latent Semantic Indexing ◽  
User Interest ◽  
User Interests ◽  
Literature Reading ◽  
Subjective Value

A literature evaluation method based on user interest is proposed by synthesizing self-values of literature and subjective values relative to query users in this paper. Firstly, in the process of mining user interests by hierarchical clustering, vector space model is employed for expressing the literature information that reflects users download behavior and the feature space is compressed by latent semantic indexing to reduce the space dimension. Secondly, subjective value of new literature relative to researchers is quantitatively evaluated in latent semantic space. Finally, the comprehensive evaluation model of literature reading value is constructed by the transformed E-measure index based on self-value and subjective value relative to query user. Experiments show that the proposed evaluation method by fully weigh subjective and objective factors of literature is more reasonable and effective compared with the traditional evaluation methods.

scholarly journals A Novel Contextual Information Recommendation Model and Its Application in e-Commerce Customer Satisfaction Management

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Feipeng Guo ◽  
Qibei Lu
Keyword(s):  
Customer Satisfaction ◽  
Collaborative Filtering ◽  
Distributed Cognition ◽  
Contextual Information ◽  
User Interest ◽  
User Interests ◽  
Good Ability ◽  
Extraction Algorithm ◽  
Collaborative Filtering Algorithm ◽  
Information Recommendation

In the current supply chain environment, distributed cognition theory tells us that various types of context information in which a recommendation is provided are important for e-commerce customer satisfaction management. However, traditional recommendation model does not consider the distributed and differentiated impact of different contexts on user needs, and it also lacks adaptive capacity of contextual recommendation service. Thus, a contextual information recommendation model based on distributed cognition theory is proposed. Firstly, the model analyzes the differential impact of various sensitive contexts and specific examples on user interest and designs a user interest extraction algorithm based on distributed cognition theory. Then, the sensitive contexts extracted from user are introduced into the process of collaborative filtering recommendation. The model calculates similarity among user interests. Finally, a novel collaborative filtering algorithm integrating with context and user similarity is designed. The experimental results in e-commerce and benchmark dataset show that this model has a good ability to extract user interest and has higher recommendation accuracy compared with other methods.

scholarly journals Evaluation of Hypermedia Tools in Terms of Usability Heuristics for English Language Teaching

2021 ◽  
pp. 133-149
Author(s):  
Vikas Rao Naidu ◽  
Shyamala Srinivas ◽  
Mahmood Al Raisi ◽  
Vishal Dattana
Keyword(s):  
Language Learning ◽  
User Satisfaction ◽  
Teaching And Learning ◽  
English Language ◽  
Learning Experience ◽  
Design Guidelines ◽  
English Language Teaching ◽  
Qualitative Assessment ◽  
Smart Devices ◽  
User Interest

The technology-assisted teaching and learning process has seen a spurt in growth in the last two decades. The education technology field has rapidly embraced new tools and techniques to enhance the student learning experience. With the evolution of multimedia elements such as digital images, audio, video, graphics, and animation, the learning supported by technology has made learning flexible and accessible in terms of time and place. With Wi-Fi enabled campuses, it is much easier for students to learn using their smart devices enabled by hypermedia content. Hypermedia, also known as active media, is the multimedia content that brings in interactivity, where the user can interact with the system, rather than viewing the content in passive mode. This helps in generating a dialogue between the system and user, sustaining user interest. Some examples of hypermedia are interactive quizzes, games, interactive videos, etc. This study aims to investigate and evaluate four interactive tools, namely FluentU, Duolingo, Livemocha, and Hello English, which are designed for language learning. A qualitative assessment of the applications, including a review of past literature on language learning using tools, was undertaken. The expert evaluation or assessment was done using Jakob Nielsen’s ten heuristics or design guidelines. The objective was to compare the applications by measuring their usability against the standard heuristics. The goal of any usability study is user satisfaction. Through this interface evaluation, the researchers have concluded for designers that could be considered during future development of hypermedia-based tools.

scholarly journals Elisitasi Kebutuhan Untuk Meningkatkan Kepuasan Pengguna Pada Sistem E-Learning Universitas Muhammadiyah Malang

2021 ◽  
Vol 4 (2) ◽  
pp. 228-237
Author(s):  
Much. Romadhoni ◽  
◽  
Wahyu Andhyka Kusuma ◽  
Keyword(s):  
Information Systems ◽  
User Satisfaction ◽  
Learning System ◽  
Narrative Form ◽  
Interview Method ◽  
Elicitation Methods ◽  
E Learning ◽  
Elicitation Process ◽  
The University ◽  
Different Characteristics

In recent years the use of information systems has changed very dramatically. Currently, many information systems are developed for various types of users. These various kinds of users have different characteristics, which makes it very difficult for organizations developing information systems to know the needs of their users. For this reason, a good and in-depth need elicitation is needed to really know the user's needs. The purpose of this study is to explore the needs of users in the E-Learning system of the University of Muhammadiyah Malang to increase user satisfaction of the system. In this study, several elicitation methods were used, namely interviews, storytelling, user personas, and storyboards. The interview method is carried out to explore the problems experienced by users when using the system. Then the results of the interview will be processed into a narrative form of storytelling and then poured into a persona document. By using the above method, you can dig deeper to get a sharper solution to the problems experienced by users. The results of these four methods have proven to be effective in the need elicitation process because these four methods are interrelated and complement each other. This study resulted in a storyboard containing recommended solutions from the results of the excavation of needs carried out on users of the University of Muhammadiyah Malang E-Learning system

scholarly journals Dynamic Modeling and Analysis of Multidimensional Hybrid Recommendation Algorithm in Tourism Itinerary Planning under the Background of Big Data

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yange Hao ◽  
Na Song
Keyword(s):  
Travel Time ◽  
User Satisfaction ◽  
Planning System ◽  
Personalized Recommendation ◽  
User Interest ◽  
Accuracy Rate ◽  
Recommendation Algorithm ◽  
Itinerary Planning ◽  
Travel Planning ◽  
Travel Recommendation

Smart tourism can provide high-quality and convenient services for different tourists, and tourism itinerary planning system can simplify tourists’ tourism preparation. In order to improve the limitation of the recommendation dimension of traditional travel planning system, this paper designs a mixed user interest model on the premise of traditional user interest modeling and combines various attributes of scenic spots to form personalized recommendation of scenic spots. Then, it uses heuristic travel planning cost-effective method to construct the corresponding travel planning system for travel planning. In terms of the accuracy rate of travel planning recommendation, the accuracy rate of multidimensional hybrid travel recommendation algorithm is 0.984, and the missing rate is 0. When the travel cost and travel time are the same and the number of scenic spots is 20–30, the memory occupation of MH algorithm is only 1/2 of that of TM algorithm. The results show that the multidimensional hybrid travel recommendation algorithm can improve the personalized travel planning of users and the travel time efficiency ratio. The results of this study have a certain reference value in improving user satisfaction with the travel planning system and reducing user interaction.

Sign in / Sign up

Export Citation Format

Share Document