Algorithm 1: Semantic Information Vector Space Alignment Methods Cosine similarity vector alignment (outline)

1. Input: $\mathit{t}\mathit{e}\mathit{x}\mathit{t} \mathit{m}\mathit{e}\mathit{s}\mathit{s}\mathit{a}\mathit{g}\mathit{e}$

2. quantitative:

3.     $\begin{array}{rr}{\mathbf{v}}_{\mathit{A}}& =\left({\mathit{w}}_{\mathit{A}\mathbf{1}},{\mathit{w}}_{\mathit{A}\mathbf{2}},\dots ,{\mathit{w}}_{\mathit{A}\mathit{n}}\right)\\ {\mathbf{v}}_{\mathit{B}}& =\left({\mathit{w}}_{\mathit{B}\mathbf{1}},{\mathit{w}}_{\mathit{B}\mathbf{2}},\dots ,{\mathit{w}}_{\mathit{B}\mathit{m}}\right)\end{array}$ //vectorization and location information

4. normalization:

5.     $\begin{array}{rr}{\mathbf{u}}_{\mathit{A}}& =\frac{{\mathbf{v}}_{\mathit{A}}}{\parallel {\mathbf{v}}_{\mathit{A}}\parallel }\\ {\mathbf{u}}_{\mathit{B}}& =\frac{{\mathbf{v}}_{\mathit{B}}}{\parallel {\mathbf{v}}_{\mathit{B}}\parallel }\end{array}$ //vector normalization

6. cosine similarity:

7.     $\mathbf{Similarity}\left({\mathbf{u}}_{\mathit{A}},{\mathbf{u}}_{\mathit{B}}\right)=\frac{{\mathbf{u}}_{\mathit{A}}·{\mathbf{u}}_{\mathit{B}}}{\parallel {\mathbf{u}}_{\mathit{A}}\parallel ·\parallel {\mathbf{u}}_{\mathit{B}}\parallel }$ //Text Similarity Determination

8.     $\mathbf{Similarity}\left({\mathbf{u}}_{\mathit{A}},{\mathbf{u}}_{\mathit{B}}\right)=\frac{\sum _{\mathit{i}=\mathbf{1}}^{\mathit{n}}{\mathit{w}}_{\mathit{A}\mathit{i}}·{\mathit{w}}_{\mathit{B}\mathit{i}}}{\sqrt{\sum _{\mathit{i}=\mathbf{1}}^{\mathit{n}}{\mathit{w}}_{\mathit{A}\mathit{i}}^{\mathbf{2}}}·\sqrt{\sum _{\mathit{i}=\mathbf{1}}^{\mathit{m}}{\mathit{w}}_{\mathit{B}\mathit{i}}^{\mathbf{2}}}}$ //Alignment of text A and text B

9. Determining text similarity: (−1 to 1) The closer to 1 the vectors are, the more similar they are.