Information Processing and Management: an International Journal

This paper develops a cooperative federated reinforcement learning (RL) strategy that enables two unmanned aerial vehicles (UAVs) to cooperate in learning and predicting the movements of an intelligent deceptive target in a given ...

• UAV cooperative learning for target detection in indoor environments is investigated.

The present work analyzes the application of deep learning in the context of digital twins (DTs) to promote the development of smart cities. According to the theoretical basis of DTs and the smart city construction, the five-...

The current study addresses the problem of retrieving a specific moment from an untrimmed video by a sentence query. Existing methods have achieved high performance by designing various structures to match visual-text relations. Yet, ...

• We, for the first time, detect and alleviate the “0s bias” in video moment retrieval.

The healthcare industry suffers from poor interoperability due to its fragmented communication systems. Each medical institution has a communication system that is not necessarily compatible with the other systems on the same network. ...

• A Hyperledger-based blockchain testing network for the healthcare industry is proposed.

We present a crowdsourced study (N = 120) that investigated the role of goal-setting on learning during search. To study the role of goal-setting, we developed a tool called the Subgoal Manager (SM). The SM was designed as a simple ...

• Assigned and self-set subgoals gave greater support for planning and monitoring.

The knowledge contained in academic literature is interesting to mine. Inspired by the idea of molecular markers tracing in the field of biochemistry, three named entities, namely, methods, datasets, and metrics, are extracted and used ...

Machine reading comprehension (MRC) is a challenging task in the field of artificial intelligence. Most existing MRC works contain a semantic matching module, either explicitly or intrinsically, to determine whether a piece of context ...

• We reveal the importance of semantic matching in Machine Reading Comprehension.

Currently, many software companies are looking to assemble a team of experts who can collaboratively carry out an assigned project in an agile manner. The most ideal members for an agile team are T-shaped experts, who not only have ...

• Using a deep learning model to identify relevant T-shaped experts for agile teams.

In recent years, neural models learned through self-supervised pretraining on large scale multilingual text or speech data have exhibited promising results for underresourced languages, especially when a relatively large amount of data ...

• Downstream performance of a multilingual speech representation model on a new, underresourced language can be improved through multilingual fine-tuning and ...

• Information behaviors of late-life migrants to a new country are investigated.
• ...

Little is known about the information behaviors of older migrants who migrate later-in-life and their settlement experiences in the host country. Through the intersectional lens of information behavior in transition theory and the ...

Influence maximization (IM) has shown wide applicability in immense fields over the past decades. Previous researches on IM mainly focused on the dyadic relationship but lacked the consideration of higher-order relationship between ...

• We explore the influence maximization problem in hypergraphs and propose an adaptive degree-based heuristic algorithm.

Federated learning (FL), as a popular distributed machine learning paradigm, has driven the integration of knowledge in ubiquitous data owners under one roof. Although designed for privacy-preservation by nature, the supposed well-...

• Investigation on people’s perception of privacy in federated learning practice.

• A hyper-spherical interest model is proposed to improve recommendation quality.

Point-of-interest (POI) recommendation helps users quickly filter out irrelevant POI by considering the spatio-temporal factor. In this paper, we address the problem of check-in preference modeling in POI recommendation, and propose a ...

With the emergence and development of deep generative models, such as the variational auto-encoders (VAEs), the research on topic modeling successfully extends to a new area: neural topic modeling, which aims to learn disentangled ...

• We propose the contrastive disentangled neural topic model based on topic embedding.

Modern information-seeking systems are becoming more interactive, mainly through asking Clarifying Questions (CQs) to refine users’ information needs. System-generated CQs may be of different qualities. However, the impact of asking ...

• A user study to explore the trajectory effects of showing clarifying questions.

With the development of 3D technology and the increase in 3D models, 2D image-based 3D model retrieval tasks have drawn increased attention from scholars. Previous works align cross-domain features via adversarial domain alignment and ...

• An end-to-end unsupervised 2D image-based 3D model retrieval framework.
• ...

• Based on machine learning methods, this study constructs an effective method to identify social bots in Chinese social media.

When public health emergencies occur, a large amount of low-credibility information is widely disseminated by social bots, and public sentiment is easily manipulated by social bots, which may pose a potential threat to the public ...

With the prosperity and development of the digital economy, many fraudsters have emerged on e-commerce platforms to fabricate fraudulent reviews to mislead consumers’ shopping decisions for profit. Moreover, in order to evade fraud ...

• A novel framework for predicting user-level stance is proposed.
• It provides a ...

Stance is defined as the expression of a speaker's standpoint towards a given target or entity. To date, the most reliable method for measuring stance is opinion surveys. However, people's increased reliance on social media makes these ...

The majority of currently available entity alignment (EA) solutions primarily rely on structural information to align entities, which is biased and disregards additional multi-source information. To compensate for inadequate structural ...

A growing number of enterprises begin to utilize user-generated content (UGC) to help build brand awareness and loyalty on social media platforms. Thus, it is important to investigate what makes UGC more helpful under the new social ...

• Constructed two high-quality datasets for social media misinformation detection.

Misinformation on social media is a nonnegligible phenomenon that causes successive adverse impacts. Numerous scholarly efforts have been devoted to automatic misinformation detection to address this problem. The effective feature is ...

• A novel methodology is proposed for fine-grained targeted financial sentiment analysis.

The increasing interest around emotions in online texts creates the demand for financial sentiment analysis. Previous studies mainly focus on coarse-grained document-/sentence-level sentiment analysis, which ignores different sentiment ...

Researchers have been aware that emotion is not one-hot encoded in emotion-relevant classification tasks, and multiple emotions can coexist in a given sentence. Recently, several works have focused on leveraging a distribution label or ...

• Identify the association between emotion categories and fine-grained emotion concepts.

• We study methods to extract skill requirements from online job advertisements.
• ...

In this paper, we compare different methods to extract skill demand from the text of job descriptions. We propose the fraction of wage variation explained by the extracted skills as a novel performance metric for the comparison of ...

Data management systems rely on a correct design of data representation and software components. The data representation scheme plays a vital role in how the data are stored, which influences the efficiency of its processing and ...

• Presenting a graph-based data representation for healthcare information.
• The ...

Computational social science has become a branch of social science that uses computationally intensive ways to investigate and model social phenomena. Exploitation on mathematics, physics, and computer sciences, and analytic approaches ...

• We apply Correlation Functions and Evolution Strategy to detect herding behavior.

Performance of text classification models tends to drop over time due to changes in data, which limits the lifetime of a pretrained model. Therefore an ability to predict a model’s ability to persist over time can help design models ...

• We shed light into the temporal persistence of existing language models.
• We ...

Describing a long video using multiple sentences, i.e., dense video captioning, is a very challenging task. Existing methods neglect the important fact that the actions of several tempos (a.k.a., frequencies) evolve with the time in ...

• One Frequency recurrent Transformer with Diversity constraint method for dense video captioning.