Back to the Roots of Genres: Text Classification by Language Function
نویسندگان
چکیده
The term “genre” covers different aspects of both texts and documents, and it has led to many classification schemes. This makes different approaches to genre identification incomparable and the task itself unclear. We introduce the linguistically motivated text classification task language function analysis, LFA, which focuses on one well-defined aspect of genres. The aim of LFA is to determine whether a text is predominantly expressive, appellative, or informative. LFA can be used in search and mining applications to efficiently filter documents of interest. Our approach to LFA relies on fast machine learning classifiers with features from different research areas. We evaluate this approach on a new corpus with 4,806 product texts from two domains. Within one domain, we correctly classify up to 82% of the texts, but differences in feature distribution limit accuracy on out-of-domain data.
منابع مشابه
Task Difficulty and Its Components: Are They Alike or Different across Different Macro-genres?
Task difficulty across different macro-genres continues to remain among less attended areas in second language development studies. This study examined the correlation between task difficulty across the descriptive, narrative, argumentative, and expository macro-genres. The three components of task difficulty (i.e., code complexity, cognitive complexity, and communicative stress) were also comp...
متن کاملPublished vs. Postgraduate Writing in Applied Linguistics: The Case of Lexical Bundles
Abstract: Lexical bundles, as building blocks of coherent discourse, have been the subject of much research in the last two decades. While many of such studies have been mainly concerned with exploring variations in the use of these word sequences across different registers and disciplines, very few have addressed the use of some particular groups of lexical bundles within some gen...
متن کاملWriters on the Move: Visualizing Composing Processes Involved in Academic Writing
The present research study aimed to explore covert processes of editing and revision which were involved in writing four different academic text genres (i.e. abstract, conclusion, data commentary, and cover letter) in English language. To this end, six EFL learners with Persian as their mother were recruited to participate in this study. All the participants attended an induction session and ea...
متن کاملThe Relationship between Iranian EFL Learners' Reading Comprehension, Vocabulary Size and Lexical Coverage of the Text: The Case of Narrative and Argumentative Genres
This study explored the relationship between EFL learners’ vocabulary size, lexical coverage of the text and reading comprehension texts (narrative & argumentative genres). To this end, 120 male and female out of 180 students studying at Talesh Azad University were selected based on their performance on the Nelson Proficiency Test. A Nelson reading proficiency test was also administered in orde...
متن کاملUsing Fuzzy LR Numbers in Bayesian Text Classifier for Classifying Persian Text Documents
Text Classification is an important research field in information retrieval and text mining. The main task in text classification is to assign text documents in predefined categories based on documents’ contents and labeled-training samples. Since word detection is a difficult and time consuming task in Persian language, Bayesian text classifier is an appropriate approach to deal with different...
متن کامل