مرکز منطقه ای اطلاع رسانی علوم و فناوری فصلنامه فناوری اطلاعات و ارتباطات ایران 2717-0411 16 59 2024 6 18 Persian Stance Detection Based On Multi-Classifier Fusion تشخيص موضع به زبان فارسی مبتنی بر طبقه بندهای چندگانه 293 304 fa مژگان فرهودی عباس طلوعی اشلقی دانشگاه آزاد اسلامی واحد علوم و تحقیقات 2022 12 5 <p style="text-align: left;"><span style="font-size: 12.0pt; font-family: 'Times New Roman',serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Nazanin; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">Stance detection (also known as stance classification, stance prediction, and stance analysis) is a recent research topic that has become an emerging paradigm of the importance of opinion-mining. The purpose of stance detection is to identify the author's viewpoint toward a specific target, which has become a key component of applications such as fake news detection, claim validation, argument search, etc. In this paper, we applied three approaches including machine learning, deep learning and transfer learning for Persian stance detection. Then we proposed a framework of multi-classifier fusion for getting final decision on output results. We used a weighted majority voting method based on the accuracy of the classifiers to combine their results. The experimental results showed the performance of the proposed multi-classifier fusion method is better than individual classifiers.</span></p> <p><span dir="RTL" lang="FA" style="font-size: 12.0pt; font-family: Nazanin; mso-ascii-font-family: 'Times New Roman'; mso-fareast-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">تشخيص موضع (که با عناوبن طبقه</span><span style="font-size: 12.0pt; font-family: 'Arial',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">&zwnj;</span><span dir="RTL" lang="FA" style="font-size: 12.0pt; font-family: Nazanin; mso-ascii-font-family: 'Times New Roman'; mso-fareast-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">بندي موضع، تحليل موضع يا پيش</span><span style="font-size: 12.0pt; font-family: 'Arial',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">&zwnj;</span><span dir="RTL" lang="FA" style="font-size: 12.0pt; font-family: Nazanin; mso-ascii-font-family: 'Times New Roman'; mso-fareast-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">بيني موضع نيز شناخته شده است) يک موضوع تحقيقاتي اخير است که به يک پارادايم نوظهور تبديل شده است. هدف از تشخيص موضع، شناسايي موضع نويسنده نسبت به يک موضوع يا ادعاي خاص بوده که به جزء کليدي کاربردهايي مانند تشخيص اخبار جعلي، اعتبارسنجي ادعا يا جستجوي استدلال تبديل شده است. در اين مقاله از سه رويکرد يادگيري ماشين، يادگيري عميق و يادگيري انتقالي براي تشخيص موضع فارسي استفاده شده و سپس با بکارگيری طبقه</span><span dir="RTL" lang="AR-SA" style="font-size: 12.0pt; font-family: 'Times New Roman',serif; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;">&zwnj;</span><span dir="RTL" lang="FA" style="font-size: 12.0pt; font-family: Nazanin; mso-ascii-font-family: 'Times New Roman'; mso-fareast-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">بندهای چندگانه، مدلی برای اخذ تصميم نهايي در مورد نتايج خروجي پيشنهاد گرديده است. برای اين منظور از روش اکثريت آرا مبتنی بر صحت طبقه&zwnj;بند</span><span style="font-size: 12.0pt; font-family: 'Arial',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">&zwnj;</span><span dir="RTL" lang="FA" style="font-size: 12.0pt; font-family: Nazanin; mso-ascii-font-family: 'Times New Roman'; mso-fareast-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">های انفرادی براي ترکيب نتايج آنها استفاده گرديد. نتايج آزمايش</span><span style="font-size: 12.0pt; font-family: 'Arial',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">&zwnj;</span><span dir="RTL" lang="FA" style="font-size: 12.0pt; font-family: Nazanin; mso-ascii-font-family: 'Times New Roman'; mso-fareast-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">ها نشان داد که عملکرد مدل پيشنهادي نسبت به عملکرد طبقه</span><span style="font-size: 12.0pt; font-family: 'Arial',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">&zwnj;</span><span dir="RTL" lang="FA" style="font-size: 12.0pt; font-family: Nazanin; mso-ascii-font-family: 'Times New Roman'; mso-fareast-font-family: 'Times New Roman'; mso-hansi-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: FA;">بندهای انفرادی پيشرفت مناسبی داشته است.</span></p> http://jour.aicti.ir/en/Article/Download/40328