[et_pb_section fb_built=”1″ _builder_version=”4.5.1″ _module_preset=”default” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/05/bg-sigma9.jpg” custom_padding=”60px||43px|||” animation_style=”slide” animation_direction=”top” hover_enabled=”0″ background_last_edited=”on|phone” background_color_gradient_end_tablet=”rgba(0,42,71,0.44)” background_color_gradient_end_phone=”rgba(0,42,71,0.44)” background_color_gradient_overlays_image_tablet=”off” background_color_gradient_overlays_image_phone=”off” locked=”off” title_text=”bg-sigma9″ parallax=”on”][et_pb_row use_custom_gutter=”on” gutter_width=”2″ make_equal=”on” module_class=”service-ti-sub” _builder_version=”4.5.1″ _module_preset=”default” width=”90%” width_tablet=”90%” width_phone=”90%” width_last_edited=”on|tablet” max_width=”1210px” max_width_tablet=”90%” max_width_phone=”90%” max_width_last_edited=”on|desktop” custom_padding=”0px||0px||true|”][et_pb_column type=”4_4″ _builder_version=”4.7.7″ _module_preset=”default”][et_pb_text _builder_version=”4.5.1″ _module_preset=”default” header_font=”Josefin Sans|700|||||||” header_text_align=”center” header_text_color=”#ffffff” header_font_size=”60px” header_line_height=”0.9em” header_2_font=”Alata|700|||||||” header_2_text_align=”center” header_2_text_color=”#ffffff” header_2_font_size=”40px” header_2_line_height=”1.5em” header_3_font=”Alata|600|||||||” header_3_text_align=”center” header_3_text_color=”#000000″ header_3_font_size=”54px” header_3_letter_spacing=”-1px” custom_margin=”30px||||false|false” header_3_font_size_tablet=”” header_3_font_size_phone=”35px” header_3_font_size_last_edited=”on|phone”]

Fake Information & Hatred Language Detection

[/et_pb_text][et_pb_text _builder_version=”4.5.1″ text_font=”Josefin Sans||||||||” text_text_color=”#ffffff” text_font_size=”20px” text_line_height=”1.5em” text_orientation=”center” text_font_size_tablet=”” text_font_size_phone=”20px” text_font_size_last_edited=”on|phone”]How Sigma’s AI platform can help monitor online sources and detect fake news and hatred language.[/et_pb_text][/et_pb_column][/et_pb_row][/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.5.1″ _module_preset=”default” locked=”off”][et_pb_row column_structure=”1_2,1_2″ use_custom_gutter=”on” gutter_width=”1″ make_equal=”on” module_class=”ser-img-text” _builder_version=”4.5.1″ _module_preset=”default” width=”90%” max_width=”1170px” max_width_tablet=”90%” max_width_phone=”” max_width_last_edited=”on|phone” custom_padding=”0px||0px||true|false” hover_enabled=”0″ locked=”off” width__hover_enabled=”on|desktop” background_enable_image=”off”][et_pb_column type=”1_2″ module_class=”ds-vertical-align” _builder_version=”4.5.1″ _module_preset=”default” background_enable_image=”off” custom_padding=”||||true|false” custom_padding_tablet=”” custom_padding_phone=”” custom_padding_last_edited=”on|phone” animation_style=”slide” animation_direction=”left”][et_pb_image src=”https://sigmacognition.ai/wp-content/uploads/2021/01/D-13-Fake1.jpg” title_text=”D-13-Fake1″ align=”center” _builder_version=”4.5.1″ _module_preset=”default”][/et_pb_image][/et_pb_column][et_pb_column type=”1_2″ module_class=”ds-vertical-align” _builder_version=”4.5.1″ _module_preset=”default” background_enable_image=”off” custom_padding=”60px|60px|60px|60px|true|true” custom_padding_tablet=”” custom_padding_phone=”30px|30px|30px|30px|true|true” custom_padding_last_edited=”on|phone” animation_style=”slide” animation_direction=”right”][et_pb_text _builder_version=”4.5.1″ _module_preset=”default” header_2_font=”Josefin Sans|700|||||||” header_2_text_align=”center” header_2_text_color=”#ffffff” header_2_font_size=”25px” header_3_font=”Livvic|700|||||||” header_3_text_align=”center” header_3_text_color=”#ffffff” header_3_font_size=”36px” header_3_line_height=”1.3em” module_alignment=”center” custom_margin=”||21px|-31px|false|false” custom_margin_tablet=”-10px||||false|false” custom_margin_phone=”-10px||||false|false” custom_margin_last_edited=”on|phone”]

The Challenge

[/et_pb_text][et_pb_text _builder_version=”4.5.1″ text_font=”Josefin Sans||||||||” text_text_color=”#ffffff” text_font_size=”18px” text_line_height=”1.5em” text_orientation=”center” text_font_size_tablet=”” text_font_size_phone=”20px” text_font_size_last_edited=”on|phone”]

The client wanted to have statistics on hate speech and fake news on social media and in the news respectively. They also wanted to classify hate speech and fake news to be able to detect trends and topics.

Sigma’s AI Natural Language Processing and Understanding platform can monitor on line sources of information and social media to, among other functions, detect fake news and hate speech.

[/et_pb_text][/et_pb_column][/et_pb_row][/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.5.1″ _module_preset=”default” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/03/D-9-Electoral-Debates.jpg” parallax=”on” parallax_method=”off” custom_margin_tablet=”40px||||false|false” custom_margin_phone=”40px||||false|false” custom_margin_last_edited=”on|phone” custom_padding=”50px||50px||true|false” top_divider_color=”#ffffff” top_divider_height=”40px” top_divider_flip=”vertical” top_divider_height_tablet=”” top_divider_height_phone=”20px” top_divider_height_last_edited=”on|phone” locked=”off”][et_pb_row column_structure=”1_2,1_2″ use_custom_gutter=”on” gutter_width=”2″ make_equal=”on” module_class=”ser-text-img” _builder_version=”4.5.1″ _module_preset=”default” width=”90%” width_tablet=”90%” width_phone=”90%” width_last_edited=”on|tablet” max_width=”1210px” max_width_tablet=”90%” max_width_phone=”90%” max_width_last_edited=”on|desktop” custom_margin=”|auto|33px|auto||” custom_padding=”0px||0px|||” locked=”off”][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_color=”#ffffff” custom_padding=”40px|25px|40px|25px|true|true” animation_style=”slide” link_option_url=”#” border_radii=”on|5px|5px|5px|5px” box_shadow_style=”preset1″ box_shadow_vertical=”0px” box_shadow_blur=”48px” box_shadow_color=”rgba(0,0,0,0)” box_shadow_color__hover_enabled=”on|desktop” box_shadow_color__hover=”rgba(162,162,162,0.5)”][et_pb_blurb title=”The Solution” url=”#” content_max_width=”100%” _builder_version=”4.5.1″ _module_preset=”default” header_font=”Josefin Sans|700|||||||” header_text_align=”center” header_text_color=”#00223f” header_font_size=”20px” header_line_height=”1.5em” body_font=”Josefin Sans||||||||” body_text_align=”left” body_text_color=”#00223f” body_font_size=”18px” body_line_height=”1.5em” module_alignment=”center” animation=”off” border_width_right_image=”8px” border_color_right_image=”rgba(0,0,0,0)” header_text_color__hover_enabled=”on|desktop” header_text_color__hover=”#1273EB”]Sigma configured its crawlers to access the sources of information requested by the client as well as reliable sources of information. The collected information was processed by Sigma’s AI Natural Language Processing and Understanding platform. It clustered similar news, found relations between them, extracted information, and compared it to the information from different sources to make a decision on the reliability of the news. It also looked for hate speech using Natural Language Processing and Understanding technology as well as machine learning.

The AI platform was adapted and fine tuned to the specific task by manually annotating a reference corpus. Sigma performed the collection and annotation of the corpus.[/et_pb_blurb][/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_enable_color=”off” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/03/D-13-Fake2.jpg” custom_padding=”0px|25px|0px|25px|false|true” custom_padding_tablet=”” custom_padding_phone=”” custom_padding_last_edited=”on|phone” animation_style=”slide” link_option_url=”#” border_radii=”on|5px|5px|5px|5px” box_shadow_style=”preset1″ box_shadow_vertical=”0px” box_shadow_blur=”48px” box_shadow_color=”rgba(0,0,0,0)” box_shadow_color__hover_enabled=”on|desktop” box_shadow_color__hover=”rgba(162,162,162,0.5)” custom_padding__hover_enabled=”on|desktop”][et_pb_divider show_divider=”off” _builder_version=”4.5.1″ _module_preset=”default” height_tablet=”200px” height_phone=”200px” height_last_edited=”on|phone” locked=”off”][/et_pb_divider][/et_pb_column][/et_pb_row][et_pb_row column_structure=”1_2,1_2″ use_custom_gutter=”on” gutter_width=”2″ make_equal=”on” module_class=”ser-img-text” _builder_version=”4.5.1″ _module_preset=”default” width=”90%” width_tablet=”90%” width_phone=”90%” width_last_edited=”on|tablet” max_width=”1210px” max_width_tablet=”90%” max_width_phone=”90%” max_width_last_edited=”on|desktop” custom_padding=”0px||0px|||” locked=”off”][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_enable_color=”off” background_image=”https://sigmacognition.ai/wp-content/uploads/2021/03/news-fake-1.jpg” background_position=”bottom_right” custom_padding=”40px|25px|40px|25px|true|true” animation_style=”slide” link_option_url=”#” border_radii=”on|5px|5px|5px|5px” box_shadow_style=”preset1″ box_shadow_vertical=”0px” box_shadow_blur=”48px” box_shadow_color=”rgba(0,0,0,0)” box_shadow_color__hover_enabled=”on|desktop” box_shadow_color__hover=”rgba(162,162,162,0.5)”][et_pb_divider show_divider=”off” _builder_version=”4.5.1″ _module_preset=”default” height=”300px” height_tablet=”200px” height_phone=”200px” height_last_edited=”on|phone” locked=”off”][/et_pb_divider][/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.5.1″ _module_preset=”default” background_color=”#ffffff” custom_padding=”40px|25px|40px|25px|true|true” animation_style=”slide” link_option_url=”#” border_radii=”on|5px|5px|5px|5px” box_shadow_style=”preset1″ box_shadow_vertical=”0px” box_shadow_blur=”48px” box_shadow_color=”rgba(0,0,0,0)” box_shadow_color__hover_enabled=”on|desktop” box_shadow_color__hover=”rgba(162,162,162,0.5)”][et_pb_blurb title=”The Outcome” url=”#” content_max_width=”100%” _builder_version=”4.5.1″ _module_preset=”default” header_font=”Josefin Sans|700|||||||” header_text_align=”center” header_text_color=”#00223f” header_font_size=”20px” header_line_height=”1.5em” body_font=”Josefin Sans||||||||” body_text_align=”left” body_text_color=”#00223f” body_font_size=”18px” body_line_height=”1.5em” module_alignment=”center” min_height_tablet=”” min_height_phone=”” min_height_last_edited=”on|phone” height_tablet=”” height_phone=”” height_last_edited=”on|desktop” animation=”off” border_width_right_image=”8px” border_color_right_image=”rgba(0,0,0,0)” header_text_color__hover_enabled=”on|desktop” header_text_color__hover=”#1273EB”]The resulting system was able to identify hate speech with 95% accuracy and fake news with over 75% accuracy.
There is a second phase in which more data is being collected and annotated to increase accuracy.[/et_pb_blurb][/et_pb_column][/et_pb_row][/et_pb_section]

ES