كليدواژه :
گويش فردي , شناسايي نويسنده , تحليل پيكرهاي , زبانشناسي حقوقي , روش دلتا
چكيده فارسي :
شناسايي هويت نويسنده يكي از حوزههاي تحقيقاتي مهم در حيطۀ زبانشناسي حقوقي است كه موضوع پژوهشهاي زبانشناختي و رايانشيِ گسترده در زبانهاي مختلف بوده است. با اين حال شواهد محدودي از پژوهشهاي صورتگرفته با موضوع شناسايي نويسنده در زبان فارسي وجود دارد. در اين پژوهش امكان شناسايي نويسندۀ يك متن با تكيه بر مفهوم گويش فردي و با استفاده از واژههاي دستوري زبان فارسي بررسي شده است. واژههاي دستوري از آن جهت كه بهطور ناخودآگاه در توليد زبان بهكار گرفته ميشوند، مستقل از موضوع متن بهكار ميروند و بسامد بالايي در متون كوتاه دارند، ميتوانند نشانگرهاي مؤثري براي كدگذاري گويش فردي و مميز سبك نويسندگان باشند. در اين پژوهش، ابتدا پيكرههايي متني از نوشتههاي پنج محقق و نويسندۀ معاصر جمعآوري و سپس با استفاده از نرمافزار خطاياب وفا، استانداردسازي شدند. با استفاده از بستۀ سبكسنجي stylo نرمافزار آماري R، واژههاي پربسامد دستوري با تواليهاي يك تا سهنگاشتي از متون استخراج شدند و سپس قابليت تفكيك متون بر اساس اين واژهها و با استفاده از تحليل مؤلفههاي اصلي و همچنين تحليل خوشهاي بر اساس مقياس فاصلهاي دلتا بررسي شد. نتايج نشان داد كه واژههاي دستوري در زبان فارسي قابليت تفكيك متون متعلق به يك نويسنده را دارند و عملكرد واژههاي تكنگاشتي بهتر از دو نگاشتي و سهنگاشتيها در متون كمحجم است. همچنين نتايج پژوهش نشان داد كه حجم كمينۀ متن براي شناسايي موفقيتآميز نويسنده در متون فارسي حدود 4000 واژه بر اساس 20 واژۀ دستوري پربسامد است.
چكيده لاتين :
The problem of discovering the identity of anonymous authors has engaged humans' attention during the ages. In present times, with the revolution brought about by digital computing and electronic corpora, and also with the applications made available by stylometry research in forensic linguistics, systematic analysis of texts in different languages has expanded the understanding of researchers on the different aspects of linguistic styles.
In the present study, the possibility of authorship attribution based on idiolect has been investigated in Farsi. One of the linguistic elements that is claimed to be the seat for idiolect is function words. Function words have been the focus of attention in the authorship attribution research since it has been shown that they are processed unconsciously, have high frequency in texts, and remain independent of text topic. In this paper, the possibility of differentiating texts written by different authors has been studied using Farsi function words. The research questions were: 1) Are Farsi functions words capable of differentiating authors in Farsi prose? 2) Of monograms, bigrams, and trigrams, which one is the most efficient in differentiating author styles? 3) What is the minimum cut-off point for successful differentiation of author styles in Farsi?
First, a corpus of five Iranian scholars’ writings was compiled, normalized and divided into different sample texts. Then 20 most frequent words were extracted from different author samples and n-gram sequences (up to tri-grams) were analyzed using principal component analysis and cluster analysis in the Stylo package of R.
Findings showed that function words in Farsi were capable of differentiating authors’ writings with monogram words performing better than bi-gram and tri-grams in small size samples. Findings also indicated that under the experimental conditions used in this study, the minimum number of words for a text to be successfully attributed to an author is about 4000 words. This cut-off point is reached using 20 most frequent function words. It is concluded that different authors don't use function words in the same manner. In fact, while some high-frequency function words appear in the writings of all authors, they are given different priorities by different authors.