Active tag recommendation for interactive entity search: Interaction effectiveness and retrieval performance

Article Computer Science, Information Systems

Does More Context Help? Effects of Context Window and Application Source on Retrieval Performance

Tung Vuong et al.

Summary: The effect of contextual information obtained from a user's digital trace on Web search performance is studied. Contextual information is modeled using Dirichlet-Hawkes processes (DHP) and used to augment Web search queries. A field study was conducted with participants installing a screen recording and digital activity monitoring system on their laptops to collect data on Web search queries and associated context. The results show that incorporating more contextual information significantly improves Web search rankings.

ACM TRANSACTIONS ON INFORMATION SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Information Systems

Hierarchical attention model for personalized tag recommendation

Jianshan Sun et al.

Summary: This study introduces a personalized tag recommendation method based on multi-information, which integrates different elements and information using a hierarchical attention model. Experimental results demonstrate that this approach can significantly enhance the performance of recommendation models.

JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Computer Science, Cybernetics

Entity Recommendation for Everyday Digital Tasks

Giulio Jacucci et al.

Summary: Recommender systems play an important role in supporting everyday digital tasks by retrieving and recommending useful information contextually, based on data captured from interactions with individual applications. This research explores the impact and usage of recommendations by utilizing comprehensive digital activity monitoring, entity-based computing and interaction, and investigating the usefulness of entity recommendations.

ACM TRANSACTIONS ON COMPUTER-HUMAN INTERACTION (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Entity summarization: State of the art and future challenges

Qingxia Liu et al.

Summary: This study focuses on entity summarization research, aiming to provide a comprehensive survey of existing methods and suggest future directions. The review revealed limitations in current methods, which mainly involve unsupervised techniques and various frameworks for combining technical features. The study identified future research directions such as the use of semantics, human factors, machine learning, and non-extractive methods to tackle the challenges in entity summarization.

JOURNAL OF WEB SEMANTICS (2021)

添加到收藏夹

Article Computer Science, Information Systems