Information credibility on twitter
Citations
710 citations
Cites background from "Information credibility on twitter"
...e.g. the public and formal response organizations) [Hiltz et al. 2011]. Automatic classification can be used to filter out content that is unlikely to be considered credible [Gupta and Kumaraguru 2012; Castillo et al. 2011]. Additionally, the public itself can be mobilized to confirm or discredit a claim through crowdsourcing [Popoola et al. 2013]. 8.2. Beyond Data Processing Designing with the users. Once social media ...
[...]
710 citations
Cites background from "Information credibility on twitter"
...However, Twitter streams contain large amounts of meaningless messages (pointless babbles) (Hurlock and Wilson 2011) and rumors (Castillo et al. 2011)....
[...]
...In addition, Twitter streams contain large amounts of meaningless messages (Hurlock and Wilson 2011), polluted content (Lee et al. 2011), and rumors (Castillo et al. 2011), which negatively affect the performance of the detection algorithms....
[...]
...2011), and rumors (Castillo et al. 2011), which negatively affect the performance of the detection algorithms....
[...]
...This assumption is clearly violated in Twitter data streams, where relevant events are buried in large amounts of noisy data (Becker et al. 2011b; Castillo et al. 2011; Hurlock and Wilson 2011; Lee et al. 2011)....
[...]
699 citations
Cites background or methods from "Information credibility on twitter"
...In contrast, our proposed features are drawn from extensive theories in social psychology and are almost non-overlapping with the feature set of [3], hence providing a complementary view to the problem....
[...]
...Table VI: The average performance for each classification method: B (baseline with 15 features from [3]), S1 (proposed in this paper with 11 features), and C (combinaton of baseline and our proposed method with 27 features)...
[...]
...In order to test whether the selected features are effective classifiers, we adopted 15 features that were used in [3] as described in Table V....
[...]
...Table V: Features for determining credibility of information described in [3], used as baseline....
[...]
...[3], which proposed a set of features to assess the credibility of social media content....
[...]
627 citations
Cites background from "Information credibility on twitter"
...Textual features are statistical or semantic features extracted from text content of posts, which have been explored in many literatures of fake news detection [4, 11, 19, 27]....
[...]
586 citations
Cites background from "Information credibility on twitter"
...showed that automated classification techniques can be used to detect news topics from conversational topics and assessed their credibility based on various Twitter features [5]....
[...]
References
6,108 citations
3,976 citations
"Information credibility on twitter" refers background in this paper
...to track epidemics [17], detect news events [28], geolocate such events [27], and find controversial emerging controversial topics [24]....
[...]
3,025 citations
"Information credibility on twitter" refers background in this paper
...In the table we have separated two broad types of topics: news and conversation, following the broad categories found in [13, 22]....
[...]
...While most messages on Twitter are conversation and chatter, people also use it to share relevant information and to report news [13, 22, 21]....
[...]
1,479 citations
Additional excerpts
...Twitter has been used widely during emergency situations, such as wildfires [6], hurricanes [12], floods [32, 33, 31] and earthquakes [15, 7]....
[...]
1,300 citations
"Information credibility on twitter" refers background in this paper
...Many of the features follow previous works including [1, 2, 12, 26]....
[...]