Crowd-Sensing with Polarized Sources

Abstract

Abstract-The paper presents a new model for crowd-sensing applications, where humans are used as the sensing sources to report information regarding the physical world. In contrast to previous work on the topic, we consider a model where the sources in question are polarized. Such might be the case, for example, in political disputes and in situations involving different communities with largely dissimilar beliefs that color their interpretation and reporting of physical world events. Reconstructing accurate ground truth is more complicated when sources are polarized. The paper describes an algorithm that significantly improves the quality of reconstruction results in the presence of polarized sources. For evaluation, we recorded human observations from Twitter for four months during a recent Egyptian uprising against the former president. We then used our algorithm to reconstruct a version of events and compared it to other versions produced by state of the art algorithms. Our analysis of the data set shows the presence of two clearly defined camps in the social network that tend of propagate largely disjoint sets of claims (which is indicative of polarization), as well as third population whose claims overlap subsets of the former two. Experiments show that, in the presence of polarization, our reconstruction tends to align more closely with ground truth in the physical world than the existing algorithms.

Credibility on Crowdsensing Data Acquisition

“…Dilruba and Naznin [125] presented a population-based reliability estimation (PBRE) by using a genetic algorithm to estimate the reliability. Amin et al [123] introduced an algorithm that performs polarityinformed maximum-likelihood estimation of statistical credibility for reported observations. Wang et al [137] modeled human participants as sources of unknown reliability by generating binary measurements of uncertain provenance.…”

“…OF NEGATIVE IMPACT ON DATA CREDIBILITYDescriptionReferences Collectors contributions may be misleading such as intentionallyfalsified An et al[81], Amintoosi and Kanhere[172], Alswailim et al[29], Zeng and Li[82], Hao et al[83], Huang et al[173], Wang et al[33], Venanzi et al[121], Hassani et al[85], Amin et al[123], Zeng et al[188], Ben et al[87], Restuccia and Das [39], Wang et al [88], Azzam et al [89], Yang et al [90], Yu et al [174], Hao et al [92], Zhou et al [158], Gao et al [93], He et al [94], Yang et al [26], Huang et al [175], Xie et al [189], Restuccia et al [160], Amintoosi and Kanhere [95], Oleson et al [129], Ben et al [96], Mashhadi and Capra [130], Naderi et al [131], Ren et al [97], Kazemi and Shahabi [193], He et al [99], Wang et al [133], Xu et al [194], Mrazovic et al [100], Manzoor et al [177], Ouyang et al [135], Meng et al [136], Wang et al [137], Yang et al [178], Riahi et al [101], Wang et al [102], Budde et al [165], Mousa et al [138], Sun et al [58], Bhattacharjee et al [179], Bajaj and Singh [105], Wu et al [141], Yu et al [180], Miao et al [197], Yang et al [181], Shao et al [142], Li et al [62], Liu et al [145], Amintoosi and Kanhere [146], Wang et al [69], Wang et al [72], Yang et al [73], Liu et al [110], Yang et al [115], Alswailim et al [147], Restuccia et al [148], Li et al [149], Kang et al [169], Zhou et al [170], Restuccia et al [171], Folorunso and Mustapha [153], and Wu et al [203] Collector's motivation to participate Sun and Ma [34], Hu et al [35], Wu and Luo [36], Zheng et al [37], Yao et al Alswailim et al [201], Chen and Zhao [202], and Alsheikh et al [204] Variety of hardware sensors and social networks as data sources Freschi et al [122], Cheng et al [7], Cheng et al [31], Delpriori et al [154], Barnwal et al [155], Dilruba and Naznin [125], Xiang et al [159], Erfani et al [191], Wang et al [132], Hung et al [134], Prandi et al [140], Jin et al [64], Krishna [66], Liu and Li [113], and Zhu et al [114] Precision issues in the hardware sensors Xiang et al [124], Saroiu and Wolman [156], Talasila et al [157], Mohssen et al [126], Bhuiyan et al [127], Ding et al [161], Gilbert et al [162], Dua et al [163], Gilbert et al [164], De Araujo et al [166], Chang and Chen [168], and Kaptan et al [150] Collector overload and high resource consumption Wang et al [84], Wang et al [86], Wang et al [98], Messaoud et al [57], Ren et al [139], Gao et al [103], Wang et al [104], Wang et al [106], Li and Cai [61], Khatib et al [107], and Tao and Song [109] Credibility approaches itself Yuan et al [176], Miao et al [167], Mousa et al [195], Gao et al [144], Mousa et al [183], Liang et al [152], Gad-ElRab and Alsharkawy [151], and Pouryazdan et al…”

The Future of Deception: Machine-Generated and Manipulated Images, Video, and Audio?

“…Such deceptive information is commonly referred to as fake (fabricated) news, which can be a form of propaganda (i.e., manipulation to advance a particular view or agenda). Information spread is particularly effective if the content resonates with the preconceptions and biases of social groups or communities because the spread will be reinforced by implied trust in information coming from other members (echo chambers and filter bubbles) [4].…”

Unveiling polarization in social networks: A matrix factorization approach

“…Please note that these models are developed according to the real-world observations reported by multiple independent works [5], [6].…”

“…Bakshy et al [5] study polarization in the context of Facebook. Amin et al [6], Kase et al [21] study crowd-sensing and fact-finders in the context of war and conflict situations. In this paper, we solve the orthogonal problem of separating the polarity classes.…”