Truth Discovery from Conflicting Multi-Valued Objects

Fang, Xiu Susie

doi:10.1145/3041021.3053374

Cited by 8 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problem of conflict resolution is still critical in different fields (social, education, etc.) [5,9].…”

Section: Resultsmentioning

confidence: 99%

Semantic-based Reconstruction of User’s Interests in Distributed Systems

Zayani¹,

Ghorbel²,

Amous³

et al. 2017

CyS

View full text Add to dashboard Cite

Generally, the user requires customized data reflecting his current needs represented in terms of interests that are stored in his profile. Therefore, taking into account user's profile is significant to improve the returned results. Day by day, the user becomes more and more active in social networks and uses different distributed systems. In this context, the problem is that the access to user's interests becomes more and more difficult mainly after updating and/or enriching the user's profile. This may produce cognitive overload problem, which is time consuming in terms of browsing the user's profile. This problem can be solved by reorganizing user's interests. Most of the proposed reorganization methods use machine learning algorithms and different similarity measures. As the user's interests are characterized by their popularity and freshness, other approaches combine these characteristics into the notion of temperature in order to keep in the profile uniquely the corresponding interests for a period of time. In this paper, we propose an approach to reconstruct the user's profile by taking into account the semantic relationships between interests and by respectively merging the temperature and the k-means learning algorithm.

show abstract

“…The problem of conflict resolution is still critical in different fields (social, education, etc.) [5,9].…”

Section: Resultsmentioning

confidence: 99%

Semantic-based Reconstruction of User’s Interests in Distributed Systems

Zayani¹,

Ghorbel²,

Amous³

et al. 2017

CyS

View full text Add to dashboard Cite

show abstract

“…Most existing truth discovery methods assume that each object has only one property. This assumption is relaxed in [5,6,16,22] and these methods are develop to solve multi-truth truth discovery problem. In [3,4,17], the authors assume that the sources are not independent.…”

Section: Related Workmentioning

confidence: 99%

On the Discovery of Continuous Truth: A Semi-supervised Approach with Partial Ground Truths

Yang

Bai

Liu

2018

Web Information Systems Engineering – WISE 2018

View full text Add to dashboard Cite

In many applications, the information regarding to the same object can be collected from multiple sources. However, these multisource data are not reported consistently. In the light of this challenge, truth discovery is emerged to identify truth for each object from multisource data. Most existing truth discovery methods assume that ground truths are completely unknown, and they focus on the exploration of unsupervised approaches to jointly estimate object truths and source reliabilities. However, in many real world applications, a set of ground truths could be partially available. In this paper, we propose a semisupervised truth discovery framework to estimate continuous object truths. With the help of ground truths, even a small amount, the accuracy of truth discovery can be improved. We formulate the semi-supervised truth discovery problem as an optimization task where object truths and source reliabilities are modeled as variables. The ground truths are modeled as a regularization term and its contribution to the source weight estimation can be controlled by a parameter. The experiments show that the proposed method is more accurate and efficient than the existing truth discovery methods.

show abstract

“…Example 1 shows and explains an application case of truth finding in the context of set expansion: in Section 3.3, we formally define the procedure. For more details about the state-of-the-art truth finding approaches and their comparative evaluation, we refer our readers to Dong and Naumann (2009), Li et al (2012), Attia Waguih and Berti-Équille (2014), Waguih et al (2015), Berti-Equille and Borge-Holthoefer (2015), Fang (2017).…”

Section: Related Workmentioning

confidence: 99%

“…Advanced approaches, using biased value confidence scores with the trustworthy levels of the input sources, have been then proposed. Those advanced approaches implement an iterative process and could be classified as follows: Agreement-based methods, including TruthFinder (Yin et al , 2008), Cosine, 2-Estimates and 3-Estimates (Galland et al , 2010), use the notion of majority to iteratively computes source trustworthiness and value confidence score until convergence. MAP estimation-based methods, including MLE (Wang et al , 2012), LTM (Zhao et al , 2012) and LCA models (Pasternack and Roth, 2013), are built on Maximum A Posteriori paradigm. Bayesian inference-based methods, including four variants of Depen models (Dong et al , 2009a) and SmartMTD (Fang, 2017; Fang et al , 2017), are based on a Bayesian analysis. …”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Set of tuples expansion by example with reliability

Abdessalem

et al. 2017

IJWIS

View full text Add to dashboard Cite

Purpose This paper aims to focus on the design of algorithms and techniques for an effective set expansion. A tool that finds and extracts candidate sets of tuples from the World Wide Web was designed and implemented. For instance, when a given user provides <Indonesia, Jakarta, Indonesian Rupiah>, <China, Beijing, Yuan Renminbi>, <Canada, Ottawa, Canadian Dollar> as seeds, our system returns tuples composed of countries with their corresponding capital cities and currency names constructed from content extracted from Web pages retrieved. Design/methodology/approach The seeds are used to query a search engine and to retrieve relevant Web pages. The seeds are also used to infer wrappers from the retrieved pages. The wrappers, in turn, are used to extract candidates. The Web pages, wrappers, seeds and candidates, as well as their relationships, are vertices and edges of a heterogeneous graph. Several options for ranking candidates from PageRank to truth finding algorithms were evaluated and compared. Remarkably, all vertices are ranked, thus providing an integrated approach to not only answer direct set expansion questions but also find the most relevant pages to expand a given set of seeds. Findings The experimental results show that leveraging the truth finding algorithm can indeed improve the level of confidence in the extracted candidates and the sources. Originality/value Current approaches on set expansion mostly support sets of atomic data expansion. This idea can be extended to the sets of tuples and extract relation instances from the Web given a handful set of tuple seeds. A truth finding algorithm is also incorporated into the approach and it is shown that it can improve the confidence level in the ranking of both candidates and sources in set of tuples expansion.

show abstract

Truth Discovery from Conflicting Multi-Valued Objects

Cited by 8 publications

References 15 publications

Semantic-based Reconstruction of User’s Interests in Distributed Systems

Semantic-based Reconstruction of User’s Interests in Distributed Systems

On the Discovery of Continuous Truth: A Semi-supervised Approach with Partial Ground Truths

Set of tuples expansion by example with reliability

Contact Info

Product

Resources

About