An Analysis on Student- Written Summaries: Automatic Assessment of Summary Writing

Summarization is a process to create a short version of a source text. As identifying summarizing strategies used by students in summary writings is a very time-consuming task, computer-assisted assessment can help teachers to identify summarizing strategies more effectively. The main goal of this investigation is to improve the abilities of students in summary writing and A study of effectiveness of summarizing strategies are used in summary writings which focused on three aspects: 1) analysis the correlation between summarizing strategies and summary performance, 2) the influence of number of summarizing strategies on students' summaries performance and 3) identifying summarizing strategies employed by the students. Results from this study displayed that there is a correlation between summarizing strategies and students 'summaries performance. The summary will improve by using more variety of summarizing strategies. The proposed algorithm is able to identify the summarizing strategies used by students in summarizing. An automatic assessment of summary based on the proposed algorithm has also been developed.

[1]  Peter N. Winograd.  Strategic difficulties in summarizing texts , 1984 .

[2]  Enrique Alfonseca,et al.  UPPER BOUNDS OF THE BLEU ALGORITHM APPLIED TO ASSESSING STUDENT ESSAYS , .

[3]  J. Wilson.  Connecting Speaking and Writing in Second Language Writing Instruction , 2008 .

[4]  Risto Miikkulainen,et al.  In Proceedings of the 19th Annual Conference of the Cognitive Science Society , 1997 .

[5]  Eduard H. Hovy,et al.  Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics , 2003, NAACL.

[6]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[7]  Ann L. Brown,et al.  The Development of Plans for Summarizing Texts , 1983 .

[8]  Pat Langley,et al.  Editorial: On Machine Learning , 1986, Machine Learning.

[9]  Hongyan Jing,et al.  Using Hidden Markov Modeling to Decompose Human-Written Summaries , 2002, Computational Linguistics.

[10]  Marita Franzke,et al.  Building Student Summarization, Writing and Reading Comprehension Skills With Guided Practice and Automated Feedback , 2006 .

[11]  Ann L. Brown,et al.  Macrorules for summarizing texts: the development of expertise , 1983 .

[12]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[13]  Benoît Lemaire,et al.  Computational cognitive models of summarization assessment skills , 2005 .

[14]  G. Miller,et al.  Contextual correlates of semantic similarity , 1991 .

[15]  Yun Tian,et al.  Measuring the similarity of short texts by word similarity and tree kernels , 2010, 2010 IEEE Youth Conference on Information, Computing and Telecommunications.

[16]  Bob Rehder,et al.  How Well Can Passage Meaning be Derived without Using Word Order? A Comparison of Latent Semantic Analysis and Humans , 1997 .

[17]  Carol Westby,et al.  Summarizing Expository Texts , 2010 .

[18]  H. P. Edmundson,et al.  New Methods in Automatic Extracting , 1969, JACM.

[19]  Siu Cheung Hui,et al.  Automatic summary assessment for intelligent tutoring systems , 2009, Comput. Educ..

[20]  Zuhair Bandar,et al.  Sentence similarity based on semantic nets and corpus statistics , 2006, IEEE Transactions on Knowledge and Data Engineering.

[21]  Patrick F. Reidy.  An Introduction to Latent Semantic Analysis , 2009 .

[22]  Alan R. Hirvela,et al.  Connecting Reading Writing in Second Language Writing Instruction , 2016 .

[23]  Dekang Lin,et al.  An Information-Theoretic Definition of Similarity , 1998, ICML.

[24]  Iraide Zipitria,et al.  From Human to Automatic Summary Evaluation , 2004, Intelligent Tutoring Systems.