Temporal, Cultural and Thematic Aspects of Web Credibility

Nielek, Radosław; Wawer, Aleksander; Jankowski-Lorek, Michał; Wierzbicki, Adam

doi:10.1007/978-3-319-03260-3_36

Cited by 6 publications

(3 citation statements)

References 12 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, some topics may be generally more trustworthy than others. These considerations, confirmed recently in [12], point to the possibility that bag-of-word representation could indeed be aligned with topic-based classification. However, the verification of this hypothesis falls out of the immediate scope of this paper and may need more robust data sets with topic labels assignment.…”

Section: Words Of High and Low Trustmentioning

confidence: 65%

Predicting webpage credibility using linguistic features

Wawer

Nielek

Wierzbicki

2014

Proceedings of the 23rd International Conference on World Wide Web

Self Cite

View full text Add to dashboard Cite

The article focuses on predicting trustworthiness from textual content of webpages. The recent work Olteanu et al. proposes a number of features (linguistic and social) to apply machine learning methods to recognize trust levels. We demonstrate that this approach can be substantially improved in two ways: by applying machine learning methods to vectors computed using psychosocial and psycholinguistic features and in a high-dimensional bag-of-words paradigm of word occurrences. Following [13], we test the methods in two classification settings, as a 2-class and 3-class scenario, and in a regression setting. In the 3-class scenario, the features compiled by [13] achieve weighted precision of 0.63, while the methods proposed in our paper raise it to 0.66 and 0.70. We also examine coefficients of the models in order to discover words associated with low and high trust.

show abstract

Section: Words Of High and Low Trustmentioning

confidence: 65%

Predicting webpage credibility using linguistic features

Wawer

Nielek

Wierzbicki

2014

Proceedings of the 23rd International Conference on World Wide Web

Self Cite

View full text Add to dashboard Cite

show abstract

“…One of the major objectives of this article is to determine how the specific background of users (demographic, sociological, or psychological profile, as well as topic of content) may affect final classifications based on evaluations uploaded by random and relatively small groups of system participants. As described by Rafalak et al [2014b], Wawer et al [2014], and Nielek et al [2013], psychosocial determinants play an important role in predicting evaluations in crowdsourcing systems dedicated to website trustworthiness. In order to explore how extreme cases affect evaluations uploaded to a quality evaluation system, for every value of an independent variable included in the analyzed datasets, random samples of size 10 are drawn (for example, for the gender variable, we draw samples of size 10 of evaluations submitted only by men and samples submitted only by women).…”

Section: Methods For Evaluating the Sensitivity Of The Sample Structurmentioning

confidence: 99%

Web Content Classification Using Distributions of Subjective Quality Evaluations

et al. 2016

Self Cite

View full text Add to dashboard Cite

Machine learning algorithms and recommender systems trained on human ratings are widely in use today. However, human ratings may be associated with a high level of uncertainty and are subjective, influenced by demographic or psychological factors. We propose a new approach to the design of object classes from human ratings: the use of entire distributions to construct classes. By avoiding aggregation for class definition, our approach loses no information and can deal with highly volatile or conflicting ratings. The approach is based the concept of the Earth Mover's Distance (EMD), a measure of distance for distributions. We evaluate the proposed approach based on four datasets obtained from diverse Web content or movie quality evaluation services or experiments. We show that clusters discovered in these datasets using the EMD measure are characterized by a consistent and simple interpretation. Quality classes defined using entire rating distributions can be fitted to clusters of distributions in the four datasets using two parameters, resulting in a good overall fit. We also consider the impact of the composition of small samples on the distributions that are the basis of our classification approach. We show that using distributions based on small samples of 10 evaluations is still robust to several demographic and psychological variables. This observation suggests that the proposed approach can be used in practice for quality evaluation, even for highly uncertain and subjective ratings.

show abstract

“…Alternatively they represent characteristics of the authority, source, and message (Rieh & Danielson, 2007). Further, literature suggests that credibility is a subjective perception and the information user perspective has to be taken into consideration (Metzger & Flanagin, 2015;Nielek et al, 2013). The understanding, experience, values, attitudes, culture and other characteristics of the user are crucial for the interpretation of facts.…”

Section: Dimensions Of Credibility In Information Science: Mapping Thmentioning

confidence: 99%

Wiarygodność informacji w epoce cyfrowej: przegląd wybranych koncepcji

Shishenkova

2016

ZIN

View full text Add to dashboard Cite

CEL/TEZA: Podstawowym celem artykułu jest prezentacja wybranych koncepcji wiarygodności informacji w odniesieniu do środowiska cyfrowego z ostatnich dziesięciu lat. Dodatkowym celem badań była próba syntetycznego ujęcia pojęć związanych z zagadnieniem wiarygodności informacji w ujęciu interdyscyplinarnym.KONCEPCJA/METODY BADAŃ: W badaniach zastosowano metodę analizy i krytyki piśmiennictwa. Uwzględniono również próby interpretacji pojęcia wiarygodności informacji w ujęciu filozoficznym, psychologicznym oraz z punktu widzenia nauki o komunikacji oraz informacji naukowej. WYNIKI I WNIOSKI: W artykule wskazano na kilka konstruktów pojęciowych związanych z pojęciem wiarygodności oraz scharakteryzowano próby ich interpretacji w kontekście badań nad informacją w ostatnich dziesięciu latach. Przedstawiono również zagadnienie wpływu środowiska cyfrowego na postrzeganie zjawiska wiarygodności informacji. W artykule stwierdzono, że dotychczasowe wyniki badań dają podstawę do dalszych dociekań nad zjawiskiem wiarygodności informacji wykraczających poza ujęcie komunikacyjne. ORYGINALNOŚĆ/WARTOŚĆ POZNAWCZA: Zaprezentowane wyniki badań stanowią głos w dyskursie naukowym, którego przedmiotem jest zagadnienie wiarygodności informacji poprzez charakterystykę jego zakresu pojęciowego i wewnętrznej złożoności oraz jego multidyscyplinarny charakter.

show abstract

Temporal, Cultural and Thematic Aspects of Web Credibility

Cited by 6 publications

References 12 publications

Predicting webpage credibility using linguistic features

Predicting webpage credibility using linguistic features

Web Content Classification Using Distributions of Subjective Quality Evaluations

Wiarygodność informacji w epoce cyfrowej: przegląd wybranych koncepcji

Contact Info

Product

Resources

About