Improve Search Results Research Articles

SMART: Search Maps and Routes/Trails of Both Subtasks and Sources to Support Complex Task‐based Search

ABSTRACTTowards the goal of constructing an agent that can assist users in completing complex tasks and searching for information from multiple sources. We propose a complex task‐supporting application, SMART (Search Maps and Routes/Trails), which combines complex task modeling through users' web activities and expands search support to include maps and routes/trails of both subtasks and sources within complex tasks through case‐based reasoning. We also summarize the results of a user study conducted to evaluate the usability of the SMART prototype system. The experimental results show that SMART could help searchers make search strategies, select information sources effectively, increase confidence during task performance, and improve search results. This highlights the value of both types of maps and routes/trails of subtasks and sources in complex task‐supporting.

Mondeca for thesaurus, autotagging and ontology management in a public health statistics platform

HealthStats NSW ( www.healthstats.nsw.gov.au ) is a public platform of complex health statistics that displays information on the health of the New South Wales population taken from many data sources. The HealthStats NSW major enhancement project uses Mondeca software to create a thesaurus and ontology which improve search results and are used for automatic webpage creation to assist ‘storytelling’ and navigation. Improving the efficiency of managing content and automating Web content production frees up time and effort of specialised health statisticians and epidemiologists to develop new content and add value to existing content. This paper explores the creation of the thesaurus and its use for autotagging, creation of the ontology component and its use for webpage creation, tweaking of the automated system, and future options for the project.

Drum boiler system water level control: A study of existing hybrid optimization algorithms

In this research, we use a variety of optimization techniques to perfect the settings of a PID controller that manages the water level in a boiler's drum. In this study, Particle Swarm Optimization (P_S OPTIMIZATION) is used alongside other optimization techniques and compared to each other. Optimization that combines bacterial foraging with Particle swarms (BFP_S) and Hybridising the Gravitational Search Algorithm along with Particle swarm (GSAP_S) seeks to improve search results. The forementioned methods were tested, and their results were compared, utilising metrics such as IS ERROR, IA ERROR, ITA ERROR, and time domain specifications.

122 DIAMOND 2.0: Updating a Pioneering Digital Platform for Study Team Workforce Development

OBJECTIVES/GOALS: There is a critical need to provide quality training for study teams. Materials need to be flexible and available at the learner’s preferred time and format. DIAMOND was developed to provide nimble education offerings that respond to the changing landscape of clinical and translational research. METHODS/STUDY POPULATION: In 2018 four CTSA institutions (the University of Michigan, the Ohio State University, Rochester University, and Tufts University) collaborated to launch the DIAMOND portal. Developed as a CTSA-wide web-based platform, DIAMOND allows members of clinical and translational research teams to widely share and access training and education resources. In 2022 a MICHR-led update of DIAMOND used principles of user centered design to improve the platform. New features include updated search functions to quickly find and sort training materials, tagging training materials to the characteristics of a translational scientist, and development of user controlled customized playlists. RESULTS/ANTICIPATED RESULTS: DIAMOND currently includes 217 training resources developed by 30 CTSA hubs and private industry. The platform has over 600 page views per day from users across the U.S. and internationally. DIAMOND includes an easy-to-use form to upload new materials to the platform. Contributors are asked to include key words and select competency domains and characteristics of a translational scientist that apply to their materials. Other new features include tagging materials to streamline and improve search results, the ability to sort materials by competency domain or characteristics of a translational scientist, and the ability for users to create and share customized, personalized playlists. DISCUSSION/SIGNIFICANCE: DIAMOND is an important tool to support workforce development for study teams. Updates to the flexible digital platform meet the needs and preferences of adult learners and busy health professionals. Lessons learned from the design process and future plans for the platform will be explored.

Optimized Deep Belief Neural Network for Semantic Change Detection in Multi-Temporal Image

Nowadays, a massive quantity of remote sensing images is utilized from tremendous earth observation platforms. For processing a wide range of remote sensing data to be transferred based on knowledge and information of them. Therefore, the necessity for providing the automated technologies to deal with multi-spectral image is done in terms of change detection. Multi-spectral images are associated with plenty of corrupted data like noise and illumination. In order to deal with such issues several techniques are utilized but they are not effective for sensitive noise and feature correlation may be missed. Several machine learning-based techniques are introduced to change detection but it is not effective for obtaining the relevant features. In other hand, the only limited datasets are available in open-source platform; therefore, the development of new proposed model is becoming difficult. In this work, an optimized deep belief neural network model is introduced based on semantic modification finding for multi-spectral images. Initially, input images with noise destruction and contrast normalization approaches are applied. Then to notice the semantic changes present in the image, the Semantic Change Detection Deep Belief Neural Network (SCD-DBN) is introduced. This research focusing on providing a change map based on balancing noise suppression and managing the edge of regions in an appropriate way. The new change detection method can automatically create features for different images and improve search results for changed regions. The projected technique shows a lower missed finding rate in the Semantic Change Detection dataset and a more ideal rate than other approaches.

Global design of an off-the-shelf objective lens with no a priori design and macro-enabled optimization

Synthesis of original optical designs is a challenging endeavor for novice lens designers. It is made more difficult when attempting to design a compound lens from off-the-shelf lenses. All but the simplest compound lenses resist ready analysis or understanding from a first-principles approach of geometric optics; however, many optical design packages include powerful optimization algorithms for both local and global searches. Despite the power of these tools, the initial construction of a starting lens and merit function remains crucial to the effective utilization of the optimizer. A workflow is presented for a generic starting design, construction of the merit function, and the optimization for a compound monochromatic objective lens composed only of commercial off-the-shelf lenses. A protocol is defined for the substitution of off-the-shelf lenses into a design with optical elements of arbitrary shape factor. Additionally, the theory and method for optimization of the shape factor via a macro in Zemax OpticStudio are provided to accelerate the substitution protocol and improve search results. The performance of the objective design is presented both before and after the off-the-shelf lens substitution and performance is compared to the design requirements. A tolerance analysis is performed and sensitivity and yield are discussed. The macro, lens design, merit function, and additional supporting code are provided.

Remote OPAC users’ search query reformulation (SQR) patterns: a transaction log analysis

PurposeUsers' search logs are implicit feedbacks on how searchers interact with online information retrieval (IR) systems. The purpose of this paper is to analyze search query reformulation (SQR) patterns of University of Dar es Salaam remote OPAC users.Design/methodology/approachQualitative and quantitative analysis of transaction logs were employed to ascertain the characteristics of search queries and the patterns in which remote OPAC users reformulate their search queries. The study covered a period of six months, commencing from January to June 2019.FindingsA total of 30,474 search hits were submitted by remote OPAC users during the period under study. Individuals from academic and research institutions, computing consortia, and telecommunication companies are the main users of the system. Most of the searches originated from North America and Europe, with few searches coming from China and India. Besides improving search results, SQRs are linked with the existence of multiple information demands as manifested by the use of heterogeneous headwords within individual search episodes.Research limitations/implicationsData collected covered only six months. Similarly, it was however not possible to analyze users' search query formulation within specific contexts such as task-based information searching.Practical implicationsA query recommendation system should be integrated into the OPAC functionalities to improve users' search experiences. Alternatively, there should be a migration to a new system that offers more advanced search features and functionalities.Originality/valueThe study has contributed new insights in SQR studies particularly on how non-institutional affiliated users translate their information needs into search queries during information searching processes.Peer reviewThe peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-09-2020-0389

SketchCleanNet — A deep learning approach to the enhancement and correction of query sketches for a 3D CAD model retrieval system

Search and retrieval remains a major research topic in several domains, including computer graphics, computer vision, engineering design, etc. A search engine requires primarily an input search query and a database of items to search from. In engineering, which is the primary context of this paper, the database consists of 3D CAD models, such as washers, pistons, connecting rods, etc. A query from a user is typically in the form of a sketch, which attempts to capture the details of a 3D model. However, sketches have certain typical defects such as gaps, over-drawn portions (multi-strokes), etc. Since the retrieved results are only as good as the input query, sketches need cleaning-up and enhancement for better retrieval results.In this paper, a deep learning approach is proposed to improve or clean the query sketches. Initially, sketches from various categories are analysed in order to understand the many possible defects that may occur. A dataset of cleaned-up or enhanced query sketches is then created based on an understanding of these defects. Consequently, an end-to-end training of a deep neural network is carried out in order to provide a mapping between the defective and the clean sketches. This network takes the defective query sketch as the input and generates a clean or an enhanced query sketch. Qualitative and quantitative comparisons of the proposed approach with other state-of-the-art techniques show that the proposed approach is effective. The results of the search engine are reported using both the defective and enhanced query sketches, and it is shown that using the enhanced query sketches from the developed approach yields improved search results.

Wikipedia as an Ontology for Describing Documents

Identifying topics and concepts associated with a set of documents is a task common to many applications. It can help in the annotation and categorization of documents and be used to model a person's current interests for improving search results, business intelligence or selecting appropriate advertisements. One approach is to associate a document with a set of topics selected from a fixed ontology or vocabulary of terms. We have investigated using Wikipedia's articles and associated pages as a topic ontology for this purpose. The benefits are that the ontology terms are developed through a social process, maintained and kept current by the Wikipedia community, represent a consensus view, and have meaning that can be understood simply by reading the associated Wikipedia page. We use Wikipedia articles and the category and article link graphs to predict concepts common to a set of documents. We describe several algorithms to aggregate and refine results, including the use of spreading activation to select the most appropriate terms. While the Wikipedia category graph can be used to predict generalized concepts, the article links graph helps by predicting more specific concepts and concepts not in the category hierarchy. Our experiments demonstrate the feasibility of extending the category system with new concepts identified as a union of pages from the page link graph.

Improving Music Streaming Services Through Metadata: Case Study from JOOX Indonesia

Background of this Study: This article examines how digital music handled on music streaming services, JOOX Indonesia in particular. Purposes: The aims was to bring insight that metadata management skill could help an enhancement over music streaming services through metadata and to improve the user experience when using music streaming services. Method:A single case study is chosen as the research method for this paper. The researcher did three months internship to see how the music file handled on the back end of JOOX. Semi-structured qualitative interviews and documentary analysis were used to collect and triangulate the qualitative data. Findings: The result shows JOOX using its operational self-possession procedures to handle its digital music file and using its own metadata standard with adaptation from music metadata standard. JOOX has a feature that utilizes music lyric. We found that lyric metadata embedded as a distinct entity on their backend system. Since lyric frequently used by the user as an access point when they do the retrieval, we propose to embed lyric as a field on music metadata to improve search result. Conclusion: These research shows are lyric as the essential part when users enjoy the music in music streaming services. By embed lyric on music metadata, lyric could be able as an access point for retrieval. Moreover, lyric as metadata could be part of music digital file handling.

Data Mining Technics and Cyber Hygiene Behaviors in Social Media

The authors present in this work information about social media and data mining usage for that. It is represented information about social networking sites, where Facebook dominates the industry by boasting an account of 85% of the internet user’s worldwide. Applying data mining techniques to large social media data sets has the potential to continue to improve search results for everyday search engines, realize specialized target marketing for businesses, help psychologist study behavior, provide new insights into social structure for sociologists, personalize web services for consumers, and even help detect and prevent spam for all of us. The most common data mining applications related to social networking sites is represented. Authors have also gave information about different data mining techniques and list of these techniques. It is important to protect personal privacy when working with social network data. Recent publications highlight the need to protect privacy as it has been shown that even anonymizing this type of data can still reveal personal information when advanced data analysis techniques are used. A whole range of different threat of social networks is represented. Authors explain cyber hygiene behaviors in social networks, such as backing up data, identity theft and online behavior.

Towards linked open government data in Canada

Governments are publishing enormous amounts of open data on the web every day in an effort to increase transparency and reusability. Linking data from multiple sources on the web enables the performance of advanced data analytics, which can lead to the development of valuable services and data products. However, Canada's open government data portals are isolated from one another and remain unlinked to other resources on the web. In this paper, we first expose the statistical data sets in Canadian provincial open data portals as Linked Data, and then integrate them using RDF Cube vocabulary, thereby making different open data portals available through a single search endpoint. We leverage Semantic Web Technologies to publish open data sets taken from two provincial portals (Nova Scotia and Alberta) as RDF (the Linked Data format), and to connect them to one another. The success of our approach illustrates its high potential for linking open government data sets across Canada, which will in turn enable greater data accessibility and improved search results.

Identifying Behavioural Intents in a Complex Search Process Management System

Understanding search intents is essential for improving search results and query recommendations. Currently, most search intent identification methods work on plain form search logs consisting of queries and clicks. Meanwhile, new search tools are being introduced by the CHI/HCI communities, allowing users to perform more types of behaviors than querying and clicking, and generating rich form search logs with more information than that in plain form search logs. In this paper, we seek to identify search intents by considering various types of behaviors performed in a complex search process management system. We use random forest to identify search intents based on the behaviors performed. Experimental results show that search intents could be identified by analyzing search behaviors, and certain types of behaviors can be good indicators of search intents.

Design, Dissemination, and Disinformation in Viral Maps

Design, Dissemination, and Disinformation in Viral Maps

An intelligent clustering approach for improving search result of a website

An intelligent clustering approach for improving search result of a website

To identify the usage of clustering techniques for improving search result of a website

Clustering has drawn much attention to research community due to its advantages and wide applications. However, clustering is a challenging problem, as many factors play a significant role. The same algorithm may generate different output if there is a change in parameters, presentation order or similarity measure. The search option is used excessively on almost every website. Grouping the search results in various folders will improve web browsing and that can be achieved by applying clustering over results. Clustering web elements facilitate data analysis in various ways. In this paper, we present well-known clustering algorithms and identify their different usages for the web elements. The paper discusses some significant work conducted in this field.

To identify the usage of clustering techniques for improving search result of a website

Clustering has drawn much attention to research community due to its advantages and wide applications. However, clustering is a challenging problem, as many factors play a significant role. The same algorithm may generate different output if there is a change in parameters, presentation order or similarity measure. The search option is used excessively on almost every website. Grouping the search results in various folders will improve web browsing and that can be achieved by applying clustering over results. Clustering web elements facilitate data analysis in various ways. In this paper, we present well-known clustering algorithms and identify their different usages for the web elements. The paper discusses some significant work conducted in this field.

A Librarian-Centered Study of Perceptions of Subject Terms and Controlled Vocabulary

ABSTRACTControlled vocabulary and subject headings in OPAC records have proven to be useful in improving search results. The authors used a survey to gather information about librarian opinions and professional use of controlled vocabulary. Data from a range of backgrounds and expertise were examined, including academic and public libraries, and technical services as well as public services professionals. Responses overall demonstrated positive opinions of the value of controlled vocabulary, including in reference interactions as well as during bibliographic instruction sessions. Results are also examined based upon factors such as age and type of librarian.

Scientometric re-ranking approach to improve search results

Common personalization approaches involve re-ranking search results. In such way, documents likely to be preferred by the user are presented higher. In this paper, we focus on research-paper retrieval. We propose a scientometric re-ranking approach based on the scientometric preferences of a particular researcher. The researcher creates its own definition of document quality by the mean of scientometric indicators. These indicators are the base of the scientometric score calculation, which serves to results re-ranking. The originality of our approach was the incorporation of different scientometric indicators into researcher’s preferences which have significantly improved ranking performance.

Using the Crowd to Improve Search Result Ranking and the Search Experience

Despite technological advances, algorithmic search systems still have difficulty with complex or subtle information needs. For example, scenarios requiring deep semantic interpretation are a challenge for computers. People, on the other hand, are well suited to solving such problems. As a result, there is an opportunity for humans and computers to collaborate during the course of a search in a way that takes advantage of the unique abilities of each. While search tools that rely on human intervention will never be able to respond as quickly as current search engines do, recent research suggests that there are scenarios where a search engine could take more time if it resulted in a much better experience. This article explores how crowdsourcing can be used at query time to augment key stages of the search pipeline. We first explore the use of crowdsourcing to improve search result ranking. When the crowd is used to replace or augment traditional retrieval components such as query expansion and relevance scoring, we find that we can increase robustness against failure for query expansion and improve overall precision for results filtering. However, the gains that we observe are limited and unlikely to make up for the extra cost and time that the crowd requires. We then explore ways to incorporate the crowd into the search process that more drastically alter the overall experience. We find that using crowd workers to support rich query understanding and result processing appears to be a more worthwhile way to make use of the crowd during search. Our results confirm that crowdsourcing can positively impact the search experience but suggest that significant changes to the search process may be required for crowdsourcing to fulfill its potential in search systems.