http://hdl.handle.net/10526/1924 The American University in Cairo Scholarly Communications community includes research findings, papers, and theses authored by students, faculty, and staff. 2013-05-23T18:52:29Z http://hdl.handle.net/10526/3536 Arabic sentence-level sentiment analysis Shoukry, Amira Magdy Sentiment analysis has recently become one of the growing areas of research related to text mining and natural language processing. The increasing availability of online resources and popularity of rich and fast resources for opinion sharing like news, online review sites and personal blogs, caused several parties such as customers, companies, and governments to start analyzing and exploring these opinions. The main task of sentiment classification is to classify a sentence (i.e. review, blog, comment, news, etc.) as holding an overall positive, negative or neutral sentiment. Most of the current studies related to this topic focus mainly on English texts with very limited resources available for other languages like Arabic, especially for the Egyptian dialect. In this research work, we would like to improve the performance measures of Egyptian dialect sentence-level sentiment analysis by proposing a hybrid approach which combines both the machine learning approach using support vector machines and the semantic orientation approach. Two methodologies were proposed, one for each approach, which were then joined, creating the hybrid proposed approach. The corpus used contains more than 20,000 Egyptian dialect tweets collected from Twitter, from which 4800 manually annotated tweets will be used (1600 positive tweets, 1600 negative tweets and 1600 neutral tweets). We performed several experiments to: 1) compare the results of each approach individually with regards to our case which is dealing with the Egyptian dialect before and after preprocessing; 2) compare the performance of merging both approaches together generating the hybrid approach against the performance of each approach separately; and 3) evaluate the effectiveness of considering negation on the performance of the hybrid approach. The results obtained show significant improvements in terms of the accuracy, precision, recall and F-measure, indicating that our proposed hybrid approach is effective in sentence-level sentiment classification. Also, the results are very promising which encourages continuing in this line of research. 2013-05-23T00:00:00Z http://hdl.handle.net/10526/3535 Texture classification using transform analysis Habib, Mary The work presented in this thesis deals with the application of spectral methods for texture classification. The aim of the present work is to introduce a hybrid methodology for texture classification based on a spatial domain global pre-classifier together with a spectral classifier that utilizes multiresolution transform analysis. The reason for developing a spatial pre-classifier is that many discriminating features of textures are present in the spatial domain of the texture. Of these, global features such as intensity histograms and entropies can still add significant information to the texture classification process. The pre-classifier uses texture intensity histograms to derive histogram moments that serve as global features. A spectral classifier that uses Hartley transform follows the pre-classifier. The choice of such transform was due to the fact that the Fast Hartley Transform has many advantages over the other transforms since it results in real valued arrays and requires less memory space and computational complexity. To test the performance of the whole classifier, 900 texture images were generated using mathematical texture generating functions. The images generated were of three different classes and each class is sub-classified into three sub-classes. Half of the generated samples was used to build the classifier, while the other half was used to test it. The pre-classifier was designed to identify texture classes using an Euclidean distance matching for 4 statistical moments of the intensity histograms. The pre-classifier matching accuracy is found to be 99.89%. The spectral classifier is designed on the basis of the Hartley transform to determine the image sub-class. Initially, a full resolution Hartley transform was used to obtain two orthogonal power spectral vectors. Peaks in these two vectors were detected after applying a 10% threshold and the highest 4 peaks for each image are selected and saved in position lookup tables. The matching accuracy obtained using the two classification phases (pre-classifier and spectral classifier) is 99.56%. The accuracy achieved for the single resolution classifier is high but that was achieved on the expense of space for the lookup tables. In order to investigate the effect of lowering the resolution on the size of the information needed for matching the textures, we have applied a multiresolution technique to the Hartley Transform in a restricted way by computing the Hartley spectra in decreasing resolution. In particular, a one-step resolution decrease achieves 99% matching efficiency while saving memory space by 40%. This is a minor sacrifice of less than 1% in the matching efficiency with a considerable decrease in the complexity of the present methodology. 2013-05-23T00:00:00Z http://hdl.handle.net/10526/3534 DeLanda's ontology: assemblage and realism Harman, Graham Manuel DeLanda is one of the few admitted realists in present-day continental philosophy, a position he claims to draw from Deleuze. DeLanda conceives of the world as made up of countless layers of assemblages, irreducible to their parts and never dissolved into larger organic wholes. This article supports DeLanda's position as a refreshing new model for continental thought. It also criticizes his movement away from singular individuals toward disembodied attractors and topological structures lying outside all specific beings. While endorsing DeLanda's realism, I reject his shift from the actual to the virtual. 2013-05-23T00:00:00Z http://hdl.handle.net/10526/3533 Zeroing in on evocative objects Harman, Graham This is a review of Sherry Turkle (Ed.), Evocative Objects, MIT Press, 352 pp. 2013-05-23T00:00:00Z