2,375 research outputs found
Rain or shine? Forecasting search process performance in exploratory search tasks
No full textMost information retrieval (IR) systems consider relevance, usefulness, and quality of information objects (documents, queries) for evaluation, prediction, and recommendation, often ignoring the underlying search process of information seeking. This may leave out opportunities for making recommendations that analyze the search process and/or recommend alternative search process instead of objects. To overcome this limitation, we investigated whether by analyzing a searcher’s current processes we could forecast his likelihood of achieving a certain level of success with respect to search performance in the future. We propose a machine-learning-based method to dynamically evaluate and predict search performance several time-steps ahead at each given time point of the search process during an exploratory search task. Our prediction method uses a collection of features extracted from expression of information need and coverage of information. For testing, we used log data collected from 4 user studies that included 216 users (96 individuals and 60 pairs). Our results show 80–90% accuracy in prediction depending on the number of time-steps ahead. In effect, the work reported here provides a framework for evaluating search processes during exploratory search tasks and predicting search performance. Importantly, the proposed approach is based on user processes and is independent of any IR system.This is the peer reviewed version of the following article: Shah, C., Hendahewa, C. and González-Ibáñez, R. (2015), Rain or shine? Forecasting search process performance in exploratory search tasks. Journal of the Association for Information Science and Technology, which has been published in final form at https://dx.doi.org/10.1002/asi.23484. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving.Peer reviewe
Capturing collabportunities: A method to evaluate collaboration opportunities in information search using pseudocollaboration
No full textIn explicit collaborative search, two or more individuals coordinate their efforts toward a shared goal. Every day, Internet users with similar information needs have the potential to collaborate. However, online search is typically performed in solitude. Existing search systems do not promote explicit collaborations, and collaboration opportunities (collabportunities) are missed. In this article, we describe a method to evaluate the feasibility of transforming these collabportunities into recommendations for explicit collaboration. We developed a technique called pseudocollaboration to evaluate the benefits and costs of collabportunities through simulations. We evaluate the performance of our method using three data sets: (a) data from single users’ search sessions, (b) data with collaborative search sessions between pairs of searchers, and (c) logs from a largescale search engine with search sessions of thousands of searchers. Our results establish when and how collabportunities would significantly help or hinder the search process versus searches conducted individually. The method that we describe has implications for the design and implementation of recommendation systems for explicit collaboration. It also connects system-mediated and user-mediated collaborative search, whereby the system evaluates the likely benefits of collaborating for a search task and helps searchers make more informed decisions on initiating and executing such a collaboration.This is the peer reviewed version of the following article: González-Ibáñez, R., Shah, C. and White, R. W. (2015), Capturing Collabportunities: A method to evaluate collaboration opportunities in information search using pseudocollaboration. Journal of the Association for Information Science and Technology, 66: 1897–1912, which has been published in final form at https://dx.doi.org/doi:10.1002/asi.23288. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Self-Archiving.Peer reviewe
The Impact Of The Development Of ICT In Several Hungarian Economic Sectors
No full textAs the author could not find a reassuring mathematical and
statistical method in the literature for studying the effect of
information communication technology on enterprises, the author
suggested a new research and analysis method that he also used to study the Hungarian economic sectors. The question of what
factors have an effect on their net income is vital for enterprises. At first, the author studied some potential indicators related to economic sectors, then those indicators were compared to the net income of the surveyed enterprises. The resulting data showed that the growing penetration of electronic marketplaces contributed to the change of the net income of enterprises to the greatest extent.
Furthermore, among all the potential indicators, it was the only indicator directly influencing the net income of enterprises.
With the help of the compound indicator and the financial data
of the studied economic sectors, the author made an attempt to find a connection between the development level of ICT and
profitability. Profitability and productivity are influenced by a lot of other factors as well. As the effect of the other factors could not be measured, the results – shown in a coordinate system - are not full but informative.
The highest increment of specific Gross Value Added was
produced by the fields of ‘Manufacturing’, ‘Electricity, gas and water supply’, ‘Transport, storage and communication’ and
‘Financial intermediation’. With the exception of ‘Electricity, gas and water supply’, the other economic sectors belong to the group of underdeveloped branches (below 50 percent).
On the other hand, ‘Construction’, ‘Health and social work’ and
‘Hotels and restaurants’ can be seen as laggards, so they got into the lower left part of the coordinate system.
‘Agriculture, hunting and forestry’ can also be classified as a
laggard economic sector, but as the effect of the compound
indicator on the increment of Gross Value Added was less
significant, it can be found in the upper left part of the coordinate system. Drawing a trend line on the points, it can be made clear that it shows a positive gradient, that is, the higher the usage of ICT devices, the higher improvement can be detected in the specific Gross Value Added
Exploring information seeking processes in collaborative search tasks
No full textMany theories and models exist for understanding and explaining information seeking processes (ISP) for individuals. Such is not the case for collaborative information seeking (CIS), despite its growing importance. In this paper we take Kuhlthau’s ISP model, designed for individual information seeking, and map it to a CIS situation. We present a laboratory study with 84 participants in 42 pairs and demonstrate how their information seeking processes over two sessions can be mapped to various stages of the ISP model. In addition, we explore the affective dimension of information seeking as well as perceived relevance expressed by the participants through their interactions. We discuss similarities and disparities of ISP for individuals and collaborative information seeking. In particular, we show that there is a logical progression from uncertainty about the task to being satisfied about the collected information among the participants; and at the same time, there is a lack of clear segmentation between stages of formulating information need, exploring information, and collecting it. The latter can be attributed to exploratory search tasks and interactions among the collaborators.Peer reviewedFirst published online Feb. 3, 2011, according to publisher's website
Evaluating the Synergic Effect of Collaboration in Information Seeking
No full textIt is typically expected that when people work together, they can often accomplish goals that are difficult or even impossible for individuals. We consider this notion of the group achieving more than the sum of all individuals' achievements to be the synergic effect in collaboration. Similar expectation exists for people working in collaboration for information seeking tasks. We, however, lack a methodology and appropriate evaluation metrics for studying and measuring the synergic effect. In this paper we demonstrate how to evaluate this effect and discuss what it means to various collaborative information seeking (CIS) situations. We present a user study with four different conditions: single user, pair of users at the same computer, pair of users at different computers and co-located, and pair of users remotely located. Each of these individuals or pairs was given the same task of information seeking and usage for the same amount of time. We then combined the outputs of single independent users to form artificial pairs, and compared against the real pairs. Not surprisingly, participants using different computers (co-located or remotely located) were able to cover more information sources than those using a single computer (single user or a pair). But more interestingly, we found that real pairs with their own computers (co-located or remotely located) were able to cover more unique and useful information than that of the artificially created pairs. This indicates that those working in collaboration achieved something greater and better than what could be achieved by adding independent users, thus, demonstrating the synergic effect. Remotely located real teams were also able to formulate a wider range of queries than those pairs that were co-located or artificially created. This shows that the collaborators working remotely were able to achieve synergy while still being able to think and work independently. Through the experiments and measurements presented here, we have also contributed a unique methodology and an evaluation metric for CIS.Peer reviewe
Hunting for hip, hipsters, and happenings on YouTube
No full textThe changing nature of information and evolving role of information sources have made it possible for almost anyone to be a consumer as well as a producer of information. Thus, many information services are focused on user participation and support different user roles. It has become essential for information scientists, social analysts, and digital library curators to recognize and study these social factors while analyzing the content of these information sources. In this paper we present these ideas in the light of our work with collecting and analyzing election videos from YouTube. Over the course of more than 8 months and 200 passes of data collection, we have gathered about 15000 videos along with nearly two dozen attributes for each video relating to US presidential elections 2008 from YouTube. Using this collection, we demonstrate how various social attributes such as tags, ratings, and comments can be used to detect significant trends, people, and events. This detection can help us gaining a better understanding of not only the content, but also the population that produces and consumes it.Peer reviewedArticle first published online June 1, 2009, according to the publisher's website
The use of information sources by Internet users in answering questions
No full textThe purpose of this study was to investigate what kinds of sources people prefer to use when they answer questions online, especially, in the context of social Q&A. Social Q&A is a Web-based service, that allows people to ask questions and receive answers from their fellow users. In social Q&A, people often cite sources of information when they answer questions. It could be a name, a short description, or hyperlinks to the original sources. Yahoo! Answers was chosen for this study due to its popularity as a top ranked social Q&A service as well as its capability for separately indicating sources for the answers in its format. We collected data with a crawler that used Yahoo! Answers APIs. A total number of 5,391 sources were identified and analyzed with the following three approaches: (1) source distribution by online accessibility, (2) source distribution by genre, and (3) source distribution by subjects. At the early stage of this study, it was expected that the results of source preferences heavily relied on sources online, since people ask and answer questions on the Web-based service. Nevertheless, it was found that human (56.4%) was the most frequently cited type of source, and it was followed by online (40%) and offline sources (4%). According to the source distribution by genre, human (56.4%) was followed by the Internet (38.1%), books (3.6%), and mass media (1.6%), and the sub-categories of these sources were analyzed. Additionally, the patterns of source distribution were shown differently across subjects. The categories of Health, Home & Electronics, and Society & Culture relied heavily on human sources, while Computers & the Internet included most of the Internet-based sources of information.Peer reviewedIssue published online June, 3, 2009; article first published online June 1, 2009, according to publisher's website. The website dates the issue as 2008
Mediapipe based Preprocessed VGGFace2 Dataset
No full textVGGFace2 Dataset and Face Mesh PreprocessingIntroductionThe VGGFace2 dataset is a large-scale face recognition dataset containing over 3.31 million images of 9,131 identities, with an average of 362 images per identity. The dataset is designed to include extensive variations in pose, age, illumination, ethnicity, and profession, making it one of the most diverse and challenging face recognition datasets available. For more details, please refer to the original publication:VGGFace2: A dataset for recognizing faces across pose and age - DOI: 10.48550/arXiv.1710.08092
Preprocessing Using MediaPipe 3D Face MeshOn this dataset, we applied the MediaPipe-based 3D face mesh algorithm to accurately detect faces while removing all background elements, including hair. Our preprocessing strictly retained facial landmarks, ensuring that only the essential facial features were preserved. This approach significantly enhanced the accuracy and generalization of our model, as the model was trained exclusively on landmark-based facial data.
Training and PerformanceThe preprocessed data was utilized to train Xception model, which resulted in remarkably accurate outcomes due to the strictly landmark-based facial representation. The model demonstrated robust performance including explainable-AI, proving that eliminating unnecessary background elements contributed positively to its efficiency and reliability.
CitationIf you use this dataset or the preprocessed version in your work, please cite both of the following:
VGGFace2 Dataset:
@article{Cao2018VGGFace2, title={VGGFace2: A dataset for recognizing faces across pose and age}, author={Cao, Qiong and Shen, Li and Xie, Weidi and Parkhi, Omkar M and Zisserman, Andrew}, journal={arXiv preprint arXiv:1710.08092}, year={2018}}
DOI: [10.48550/arXiv.1710.08092](https://doi.org/10.48550/arXiv.1710.08092) Preprocessed Dataset using MediaPipe:@dataset{Shah2025_MediaPipe_FaceMesh, title={MediaPipe-based 3D Face Mesh Preprocessed VGGFace2 Dataset}, author={Shah, Syed Taimoor Hussain and Shah, Syed Adil Hussain and Zamir, Ammara and Qayyum, Kainat and Shah, Syed Baqir Hussain and Fatima, Syeda Maryam and Deriu, Marco Agostino}, year={2025}, doi={10.5281/zenodo.15078557}} DOI: [10.5281/zenodo.15078557](https://doi.org/10.5281/zenodo.15078557)
ContactFor any questions or further details, please feel free to contact us.Syed Taimoor Hussain ShahPolitoBIOMed Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Turin, ItalyEmail: [email protected]: 0000-0002-6010-677
Ketchup Clothes: Explorations in Recycling
No full textThis booklet documents garments made from found and discarded materials under the auspices of ketchupclothes from 2004 to the present day. It is estimated that some 350,000 tonnes of clothes are assigned to landfill every year from the UK alone. This catalogue of ideas hopes to provide inspiration into what can be done with textile and clothing waste.It begins with approaches to different materials such as denim, leather and old t-shirts and progresses through a series of photoshoots that contextualise the clothes within a local, urban environment.
It concludes with current developments by the author into pattern cutting and manufacturing process that have resonance for the wider adoption of recycling practices. All garments have been designed and manufactured by the author on industrial sewing machines. These include a lockstitch, overlocker and coverstitch machin
- …
