Symbol	Description	Data Structure	Supporting Process
T	Number of Weibo posts	Int T	w-LDA
U	Number of Weibo users	Int U
K	Number of topics	Int K
V	Number of words in the vocabulary	Int V
V	Number of uers profiles	Int V
Np	Number of words in p-th user profile	Int N[P]
$\mathit{\alpha }$	K-dimensional prior weight vectors of topics in a document,	Float a[K]
$\mathit{\beta }$	V-dimensional vector prior weight of words in a topic	Float b[V]
${\mathit{\phi }}_{\mathit{z}}$	V-dimensional vector of probabilities, represents distribution of words in topic z	Double phi [Z][V]
${\mathit{\vartheta }}_{\mathit{p}}$	K-dimensional vector of probabilities, represents distribution of topics in user profile p	Double theta [P][K]
$z_i$	Identity of current topic of word $w_i$ in user profile $p_i$	Int 1…K
$w_i$	Identity of current word in user profile $p_i$	Int 1…V
$p_i$	Identity of current user profiles	Int 1…P
$n_{i,j}^{\left(p_i\right)}$	Document-Topic matrix, the number of times topic j has been assigned to words in user profile $p_i$.	int npt [P][K]
$n_{i,j}^{\left(w_i\right)}$	Topic-Word matrix, Number of times that word $w_i$ has been assigned to topic j	int ntw [K][V]
Wi	Identity of current word vector (200 dimensions) trained by traffic word2vec	Double [200]	Similarity measure
${\mathit{T}}_{\mathit{w}}^{\left(\mathit{i}=\mathit{1}\dots \mathit{K}\right)}$	Identity of current topic word cluster detected from Weibo	Double tw[K]
${\mathit{T}}_{\mathit{n}}^{\left(\mathit{j}=\mathit{1}\dots \mathit{K}\right)}$	Identity of current topic word cluster detected from News	Double tn[K]
$\mathit{W}{\mathit{E}}_w^{\left(m,i\right)}$	Word embedding- cluster tensor, identity of the current word embedding in i-th cluster detected from Weibo	Double cew[K] [Wi]
$\mathit{W}{\mathit{E}}_n^{\left(n,j\right)}$	Word embedding- cluster tensor, identity of the current word embedding in i-th cluster detected from News	Double cen [K] [Wi]
$di{s}_R\left(\mathit{W}{\mathit{E}}_w^{\left(m,i\right)},\mathit{W}{\mathit{E}}_n^{\left(n,j\right)}\right)$	Words similarity, measure the similarity between word embedding $\mathit{W}{\mathit{E}}_w^{\left(m,i\right)}$ and $\mathit{W}{\mathit{E}}_n^{\left(n,j\right)}$	Double wd
${\mathit{D}}_{\mathit{R}}\left( {\mathit{T}}_{\mathit{w}}^{\left(\mathit{i}\right)}, {\mathit{T}}_{\mathit{n}}^{\left(\mathit{j}\right)}\right)$	Topic similarity matrix, measure the distances between each words in the given topic cluster ${\mathit{T}}_{\mathit{w}}^{\left(\mathit{i}\right)}$ and ${\mathit{T}}_{\mathit{n}}^{\left(\mathit{j}\right)}$	Double td[K][K]	Event fusion
${\mu }_R\left({\mathit{T}}_{\mathit{w}}^{\left(\mathit{i}\right)},{\mathit{T}}_{\mathit{n}}^{\left(\mathit{j}\right)}\right)$	Average shortest distance between ${\mathit{T}}_{\mathit{w}}^{\left(\mathit{i}\right)}$ and ${\mathit{T}}_{\mathit{n}}^{\left(\mathit{j}\right)}$	Double atd
${\mu }_R^{*}\left({\mathit{T}}_{\mathit{w}}^{\left(\mathit{i}\right)},T_{\mathit{n}}^{\left(\mathit{j}\right)}\right)$	Normalized average shortest distance between ${\mathit{T}}_{\mathit{w}}^{\left(\mathit{i}\right)}$ and ${\mathit{T}}_{\mathit{n}}^{\left(\mathit{j}\right)}$	Double natd
${\mathsf{\sigma }}_R^{*}\left({\mathit{T}}_{\mathit{w}}^{\left(\mathit{i}\right)},{\mathit{T}}_{\mathit{n}}^{\left(\mathit{j}\right)}\right)$	The standard deviation of normalized topic distances	Double sd