Comparing Twitter Summarization Algorithms for Multiple Post Summaries
Citations
144 citations
Cites methods from "Comparing Twitter Summarization Alg..."
...Another, simpler task design has been used by [63] for evaluation of tweet summaries....
[...]
132 citations
Cites background or methods from "Comparing Twitter Summarization Alg..."
...Although there exist numerous studies on document summarization [6, 26, 23, 13, 9, 11], these methods cannot satisfy our requirements, because: (1) They mainly focus on static and small-sized datasets, making it intractable to improve their efficiency....
[...]
...ClusterSum [13]: first clusters the tweets and then summarizes each cluster by picking the most weighted post according to the hybrid TF-IDF weighting described in [13]....
[...]
...proposed a modified Hybrid TFIDF algorithm and a Cluster-based algorithm to generate multiple post summaries [13]....
[...]
109 citations
Cites background from "Comparing Twitter Summarization Alg..."
...idf can not be directly used on them [6]....
[...]
97 citations
90 citations
Cites background or methods from "Comparing Twitter Summarization Alg..."
...IDF: Introduced by Inouye and Kalita [44], the hybrid TF....
[...]
...In other words, the likelihood of words appearing in a humangenerated summary is positively correlated with their frequency [44]....
[...]
...• Hybrid TF.IDF: Introduced by Inouye and Kalita [44], the hybrid TF.IDF approach is a frequency-based summarization technique that is designed to summarize social media data....
[...]
...In our analysis, we investigate the performance of a number of extractive summarization techniques that have been shown to work well in the context of mirco-blogging data on social media [44], [43], [45], [39]....
[...]
...This hybrid modification over classical single-document TF is necessary to capture concerns that are frequent over the entire collection [44]....
[...]
References
14,696 citations
"Comparing Twitter Summarization Alg..." refers background or methods in this paper
...…length k for the summary, output a set of representative posts S with a cardinality of k such that 1) ∀s ∈ S, T is in the text of s, and 2) ∀si,∀sj ∈ S, si 6∼ sj . si 6∼ sj means that the two posts provide sufficiently different information in order to keep the summaries from being redundant....
[...]
...The TextRank algorithm [8] is also a graph-based approach that finds the most highly ranked sentences (or keywords) in a document using the PageRank algorithm [9]....
[...]
13,327 citations
7,539 citations
"Comparing Twitter Summarization Alg..." refers background in this paper
...…length k for the summary, output a set of representative posts S with a cardinality of k such that 1) ∀s ∈ S, T is in the text of s, and 2) ∀si,∀sj ∈ S, si 6∼ sj . si 6∼ sj means that the two posts provide sufficiently different information in order to keep the summaries from being redundant....
[...]
4,283 citations
3,891 citations