916a8bd8360f69730d5f1e2b2fa5aee8 appsci_a2020v10n22p8170.pdf 242b0b85ab8d7fda3d52e0ebbb67fc837e623339 appsci_a2020v10n22p8170.pdf 127014f75fb0df7cf73efb358a6112e60cc8e433c939d92aeaa87f196e3f9a35 appsci_a2020v10n22p8170.pdf Title: Personality Trait Analysis in Social Networks Based on Weakly Supervised Learning of Shared Images Subject: Social networks have attracted the attention of psychologists, as the behavior of users can be used to assess personality traits, and to detect sentiments and critical mental situations such as depression or suicidal tendencies. Recently, the increasing amount of image uploads to social networks has shifted the focus from text to image-based personality assessment. However, obtaining the ground-truth requires giving personality questionnaires to the users, making the process very costly and slow, and hindering research on large populations. In this paper, we demonstrate that it is possible to predict which images are most associated with each personality trait of the OCEAN personality model, without requiring ground-truth personality labels. Namely, we present a weakly supervised framework which shows that the personality scores obtained using specific images textually associated with particular personality traits are highly correlated with scores obtained using standard text-based personality questionnaires. We trained an OCEAN trait model based on Convolutional Neural Networks (CNNs), learned from 120K pictures posted with specific textual hashtags, to infer whether the personality scores from the images uploaded by users are consistent with those scores obtained from text. In order to validate our claims, we performed a personality test on a heterogeneous group of 280 human subjects, showing that our model successfully predicts which kind of image will match a person with a given level of a trait. Looking at the results, we obtained evidence that personality is not only correlated with text, but with image content too. Interestingly, different visual patterns emerged from those images most liked by persons with a particular personality trait: for instance, pictures most associated with high conscientiousness usually contained healthy food, while low conscientiousness pictures contained injuries, guns, and alcohol. These findings could pave the way to complement text-based personality questionnaires with image-based questions. Keywords: sentiment analysis, personality trait analysis; weakly-supervised learning; visual classification; OCEAN model; social networks Author: Pau Rodríguez, Diego Velazquez, Guillem Cucurul, Josep M. Gonfaus, F. Xavier Roca, Seiichi Ozawa and Jordi Gonzàlez Creator: LaTeX with hyperref package Producer: pdfTeX-1.40.18 CreationDate: Wed Nov 18 14:43:49 2020 CET ModDate: Thu Nov 19 02:24:34 2020 CET Custom Metadata: no Metadata Stream: no Tagged: no UserProperties: no Suspects: no Form: none JavaScript: no Pages: 15 Encrypted: no Page size: 595.276 x 841.89 pts (A4) Page rot: 0 File size: 10684066 bytes Optimized: no PDF version: 1.7 name type encoding emb sub uni object ID ------------------------------------ ----------------- ---------------- --- --- --- --------- QDPBZV+URWPalladioL-Bold Type 1 Custom yes yes no 10 0 FQBXVU+URWPalladioL-Roma Type 1 Custom yes yes no 15 0 FDXYXX+URWPalladioL-Ital Type 1 Custom yes yes no 19 0 CRVMKC+TimesNewRomanPS-BoldItalicMT Type 1C WinAnsi yes yes no 27 0 MCBCCI+SourceSansRoman-Regular Type 1C Custom yes yes no 49 0 MCBCCM+SourceSansRoman.613wght Type 1C Custom yes yes no 53 0 MCBCCO+SourceSansRoman-Bold Type 1C Custom yes yes no 57 0 AMTJWM+CMSY10 Type 1 Builtin yes yes no 67 0 CZKGAS+CMR10 Type 1 Builtin yes yes no 74 0 QQQVVD+PazoMath-Italic Type 1 Builtin yes yes no 85 0 TBWKCY+CMSY9 Type 1 Builtin yes yes no 104 0 [none] Type 3 Custom yes no yes 125 0 [none] Type 3 Custom yes no yes 149 0 [none] Type 3 Custom yes no yes 173 0 [none] Type 3 Custom yes no yes 200 0 [none] Type 3 Custom yes no yes 227 0 [none] Type 3 Custom yes no yes 252 0 [none] Type 3 Custom yes no yes 270 0 [none] Type 3 Custom yes no no 274 0 [none] Type 3 Custom yes no yes 297 0 [none] Type 3 Custom yes no yes 333 0 [none] Type 3 Custom yes no yes 368 0 [none] Type 3 Custom yes no no 404 0 [none] Type 3 Custom yes no yes 439 0 [none] Type 3 Custom yes no yes 474 0 [none] Type 3 Custom yes no no 501 0 [none] Type 3 Custom yes no yes 512 0 [none] Type 3 Custom yes no no 526 0 [none] Type 3 Custom yes no yes 532 0 [none] Type 3 Custom yes no yes 543 0 Jhove (Rel. 1.28.0, 2023-05-18) Date: 2024-10-02 04:24:05 CEST RepresentationInformation: appsci_a2020v10n22p8170.pdf ReportingModule: PDF-hul, Rel. 1.12.4 (2023-03-16) LastModified: 2023-03-31 11:39:46 CEST Size: 10684066 Format: PDF Version: 1.7 Status: Well-Formed and valid SignatureMatches: PDF-hul MIMEtype: application/pdf PDFMetadata: Objects: 708 FreeObjects: 1 IncrementalUpdates: 0 DocumentCatalog: PageLayout: SinglePage PageMode: UseNone Outlines: Item: Title: Introduction Destination: section.1 Item: Title: Related Work Destination: section.2 Children: Item: Title: Text-Based Personality Inference Destination: subsection.2.1 Item: Title: Image-Based Personality Inference Destination: subsection.2.2 Item: Title: Methodology Destination: section.3 Item: Title: Experimental Evaluation of Psychological Traits Destination: section.4 Children: Item: Title: Comparing Image Classification with Human-Based Classification Destination: subsection.4.1 Item: Title: Qualitative Results Destination: subsection.4.2 Item: Title: Conclusions Destination: section.5 Item: Title: References Destination: section.5 Info: Title: Personality Trait Analysis in Social Networks Based on Weakly Supervised Learning of Shared Images Author: Pau Rodríguez, Diego Velazquez, Guillem Cucurul, Josep M. Gonfaus, F. Xavier Roca, Seiichi Ozawa and Jordi Gonzàlez Subject: Social networks have attracted the attention of psychologists, as the behavior of users can be used to assess personality traits, and to detect sentiments and critical mental situations such as depression or suicidal tendencies. Recently, the increasing amount of image uploads to social networks has shifted the focus from text to image-based personality assessment. However, obtaining the ground-truth requires giving personality questionnaires to the users, making the process very costly and slow, and hindering research on large populations. In this paper, we demonstrate that it is possible to predict which images are most associated with each personality trait of the OCEAN personality model, without requiring ground-truth personality labels. Namely, we present a weakly supervised framework which shows that the personality scores obtained using specific images textually associated with particular personality traits are highly correlated with scores obtained using standard text-based personality questionnaires. We trained an OCEAN trait model based on Convolutional Neural Networks (CNNs), learned from 120K pictures posted with specific textual hashtags, to infer whether the personality scores from the images uploaded by users are consistent with those scores obtained from text. In order to validate our claims, we performed a personality test on a heterogeneous group of 280 human subjects, showing that our model successfully predicts which kind of image will match a person with a given level of a trait. Looking at the results, we obtained evidence that personality is not only correlated with text, but with image content too. Interestingly, different visual patterns emerged from those images most liked by persons with a particular personality trait: for instance, pictures most associated with high conscientiousness usually contained healthy food, while low conscientiousness pictures contained injuries, guns, and alcohol. These findings could pave the way to complement text-based personality questionnaires with image-based questions. Keywords: sentiment analysis, personality trait analysis; weakly-supervised learning; visual classification; OCEAN model; social networks Creator: LaTeX with hyperref package Producer: pdfTeX-1.40.18 CreationDate: Wed Nov 18 14:43:49 CET 2020 ModDate: Thu Nov 19 02:24:34 CET 2020 ID: 0xf5f6e29af4a702b491ab7b908e1c505a, 0xf5f6e29af4a702b491ab7b908e1c505a Filters: FilterPipeline: FlateDecode FilterPipeline: DCTDecode Images: Image: NisoImageMetadata: FormatName: image/png ImageWidth: 1056 ImageHeight: 981 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 800 ImageHeight: 600 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 800 ImageHeight: 600 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/png ImageWidth: 312 ImageHeight: 296 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/jpg CompressionScheme: JPEG ImageWidth: 320 ImageHeight: 320 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Image: NisoImageMetadata: FormatName: image/png ImageWidth: 625 ImageHeight: 625 ColorSpace: RGB BitsPerSample: 8 BitsPerSampleUnit: integer Filter: FlateDecode Fonts: Type1: Font: BaseFont: FDXYXX+URWPalladioL-Ital FontSubset: true FirstChar: 2 LastChar: 121 FontDescriptor: FontName: FDXYXX+URWPalladioL-Ital Flags: Symbolic FontBBox: -170, -305, 1010, 941 FontFile: true EncodingDictionary: Differences: true Font: BaseFont: AMTJWM+CMSY10 FontSubset: true FirstChar: 0 LastChar: 106 FontDescriptor: FontName: AMTJWM+CMSY10 Flags: Symbolic FontBBox: -29, -960, 1116, 775 FontFile: true Font: BaseFont: QQQVVD+PazoMath-Italic FontSubset: true FirstChar: 113 LastChar: 114 FontDescriptor: FontName: QQQVVD+PazoMath-Italic Flags: Symbolic FontBBox: -70, -277, 902, 733 FontFile: true Font: BaseFont: TBWKCY+CMSY9 FontSubset: true FirstChar: 13 LastChar: 15 FontDescriptor: FontName: TBWKCY+CMSY9 Flags: Symbolic FontBBox: -29, -958, 1146, 777 FontFile: true Font: BaseFont: QDPBZV+URWPalladioL-Bold FontSubset: true FirstChar: 3 LastChar: 237 FontDescriptor: FontName: QDPBZV+URWPalladioL-Bold Flags: Symbolic FontBBox: -152, -301, 1000, 935 FontFile: true EncodingDictionary: Differences: true Font: BaseFont: CZKGAS+CMR10 FontSubset: true FirstChar: 40 LastChar: 61 FontDescriptor: FontName: CZKGAS+CMR10 Flags: Symbolic FontBBox: -40, -250, 1009, 750 FontFile: true Font: BaseFont: FQBXVU+URWPalladioL-Roma FontSubset: true FirstChar: 2 LastChar: 242 FontDescriptor: FontName: FQBXVU+URWPalladioL-Roma Flags: Symbolic FontBBox: -166, -283, 1021, 943 FontFile: true EncodingDictionary: Differences: true Pages: Page: Sequence: 1 Annotations: Annotation: Subtype: Link Rect: 75, 757, 216, 793 Annotation: Subtype: Link Rect: 474, 757, 519, 793 Annotation: Subtype: Link Rect: 424, 660, 435, 674 Annotation: Subtype: Link Rect: 251, 647, 262, 660 Annotation: Subtype: Link Rect: 174, 38, 253, 50 Annotation: Subtype: Link Rect: 400, 38, 519, 50 Annotation: Subtype: Link Rect: 466, 520, 518, 539 Page: Sequence: 2 Annotations: Annotation: Subtype: Link Rect: 313, 702, 320, 711 ActionDest: 567 Annotation: Subtype: Link Rect: 323, 702, 330, 711 ActionDest: 570 Annotation: Subtype: Link Rect: 508, 675, 515, 684 ActionDest: 570 Annotation: Subtype: Link Rect: 473, 661, 480, 670 ActionDest: 570 Annotation: Subtype: Link Rect: 300, 648, 307, 657 ActionDest: 570 Annotation: Subtype: Link Rect: 307, 648, 314, 657 ActionDest: 570 Annotation: Subtype: Link Rect: 368, 634, 375, 643 ActionDest: 570 Annotation: Subtype: Link Rect: 276, 594, 288, 603 ActionDest: 570 Annotation: Subtype: Link Rect: 353, 567, 365, 576 ActionDest: 570 Annotation: Subtype: Link Rect: 310, 540, 322, 549 ActionDest: 570 Annotation: Subtype: Link Rect: 390, 524, 397, 536 ActionDest: 78 Annotation: Subtype: Link Rect: 324, 513, 336, 522 ActionDest: 570 Annotation: Subtype: Link Rect: 134, 364, 146, 373 ActionDest: 570 Annotation: Subtype: Link Rect: 149, 364, 161, 373 ActionDest: 570 Annotation: Subtype: Link Rect: 329, 351, 341, 360 ActionDest: 570 Annotation: Subtype: Link Rect: 341, 351, 353, 360 ActionDest: 570 Annotation: Subtype: Link Rect: 373, 310, 385, 319 ActionDest: 570 Annotation: Subtype: Link Rect: 445, 310, 457, 319 ActionDest: 570 Annotation: Subtype: Link Rect: 226, 256, 233, 265 ActionDest: 570 Annotation: Subtype: Link Rect: 233, 256, 240, 265 ActionDest: 570 Annotation: Subtype: Link Rect: 241, 256, 253, 265 ActionDest: 570 Annotation: Subtype: Link Rect: 253, 256, 265, 265 ActionDest: 570 Annotation: Subtype: Link Rect: 229, 189, 241, 198 ActionDest: 570 Annotation: Subtype: Link Rect: 326, 189, 338, 198 ActionDest: 570 Page: Sequence: 3 Annotations: Annotation: Subtype: Link Rect: 234, 667, 246, 676 ActionDest: 570 Annotation: Subtype: Link Rect: 116, 432, 128, 441 ActionDest: 570 Annotation: Subtype: Link Rect: 163, 364, 170, 373 ActionDest: 570 Annotation: Subtype: Link Rect: 414, 337, 426, 346 ActionDest: 570 Annotation: Subtype: Link Rect: 242, 310, 249, 319 ActionDest: 570 Annotation: Subtype: Link Rect: 451, 241, 463, 250 ActionDest: 570 Annotation: Subtype: Link Rect: 166, 200, 173, 209 ActionDest: 570 Annotation: Subtype: Link Rect: 305, 159, 317, 169 ActionDest: 570 Annotation: Subtype: Link Rect: 419, 106, 431, 115 ActionDest: 570 Page: Sequence: 4 Annotations: Annotation: Subtype: Link Rect: 165, 743, 177, 751 ActionDest: 570 Annotation: Subtype: Link Rect: 373, 675, 385, 684 ActionDest: 570 Annotation: Subtype: Link Rect: 217, 648, 229, 657 ActionDest: 570 Annotation: Subtype: Link Rect: 445, 607, 452, 616 ActionDest: 570 Annotation: Subtype: Link Rect: 176, 553, 188, 562 ActionDest: 570 Annotation: Subtype: Link Rect: 503, 472, 515, 481 ActionDest: 573 Annotation: Subtype: Link Rect: 121, 378, 133, 387 ActionDest: 573 Annotation: Subtype: Link Rect: 137, 297, 149, 306 ActionDest: 570 Annotation: Subtype: Link Rect: 75, 226, 249, 238 Annotation: Subtype: Link Rect: 230, 186, 242, 195 ActionDest: 570 Page: Sequence: 5 Annotations: Annotation: Subtype: Link Rect: 281, 729, 293, 738 ActionDest: 570 Annotation: Subtype: Link Rect: 337, 726, 343, 738 ActionDest: 78 Annotation: Subtype: Link Rect: 142, 651, 153, 659 ActionDest: 570 Annotation: Subtype: Link Rect: 333, 314, 345, 323 ActionDest: 573 Annotation: Subtype: Link Rect: 348, 314, 360, 323 ActionDest: 573 Annotation: Subtype: Link Rect: 468, 314, 480, 323 ActionDest: 573 Annotation: Subtype: Link Rect: 468, 260, 480, 269 ActionDest: 573 Annotation: Subtype: Link Rect: 96, 247, 108, 256 ActionDest: 573 Annotation: Subtype: Link Rect: 399, 230, 406, 243 ActionDest: 78 Annotation: Subtype: Link Rect: 187, 176, 194, 188 ActionDest: 78 Annotation: Subtype: Link Rect: 142, 149, 149, 161 ActionDest: 81 Annotation: Subtype: Link Rect: 406, 112, 418, 121 ActionDest: 570 Page: Sequence: 6 Annotations: Annotation: Subtype: Link Rect: 202, 394, 208, 405 ActionDest: 78 Annotation: Subtype: Link Rect: 131, 132, 143, 141 ActionDest: 573 Page: Sequence: 7 Annotations: Annotation: Subtype: Link Rect: 344, 702, 351, 711 ActionDest: 570 Annotation: Subtype: Link Rect: 351, 702, 363, 711 ActionDest: 573 Annotation: Subtype: Link Rect: 304, 607, 311, 616 ActionDest: 570 Annotation: Subtype: Link Rect: 311, 607, 323, 616 ActionDest: 573 Annotation: Subtype: Link Rect: 327, 607, 338, 616 ActionDest: 573 Annotation: Subtype: Link Rect: 504, 594, 516, 603 ActionDest: 573 Annotation: Subtype: Link Rect: 172, 486, 184, 495 ActionDest: 573 Annotation: Subtype: Link Rect: 451, 486, 463, 495 ActionDest: 573 Annotation: Subtype: Link Rect: 250, 432, 262, 441 ActionDest: 573 Annotation: Subtype: Link Rect: 454, 278, 461, 290 ActionDest: 94 Annotation: Subtype: Link Rect: 339, 146, 350, 155 ActionDest: 573 Page: Sequence: 8 Annotations: Annotation: Subtype: Link Rect: 299, 456, 306, 468 ActionDest: 117 Annotation: Subtype: Link Rect: 182, 415, 189, 427 ActionDest: 78 Annotation: Subtype: Link Rect: 207, 348, 215, 360 ActionDest: 117 Annotation: Subtype: Link Rect: 141, 307, 148, 319 ActionDest: 117 Annotation: Subtype: Link Rect: 377, 243, 389, 252 ActionDest: 570 Annotation: Subtype: Link Rect: 473, 243, 485, 252 ActionDest: 570 Annotation: Subtype: Link Rect: 122, 213, 129, 225 ActionDest: 291 Annotation: Subtype: Link Rect: 254, 186, 261, 198 ActionDest: 291 Annotation: Subtype: Link Rect: 463, 159, 470, 171 ActionDest: 291 Annotation: Subtype: Link Rect: 197, 73, 204, 85 ActionDest: 291 Page: Sequence: 9 Page: Sequence: 10 Page: Sequence: 11 Annotations: Annotation: Subtype: Link Rect: 503, 165, 515, 174 ActionDest: 573 Annotation: Subtype: Link Rect: 139, 82, 146, 94 ActionDest: 554 Page: Sequence: 12 Page: Sequence: 13 Annotations: Annotation: Subtype: Link Rect: 288, 729, 300, 738 ActionDest: 570 Annotation: Subtype: Link Rect: 90, 540, 101, 549 ActionDest: 573 Annotation: Subtype: Link Rect: 167, 103, 205, 113 Annotation: Subtype: Link Rect: 479, 76, 516, 87 Page: Sequence: 14 Annotations: Annotation: Subtype: Link Rect: 317, 714, 355, 725 Annotation: Subtype: Link Rect: 287, 688, 325, 699 Annotation: Subtype: Link Rect: 469, 637, 507, 648 Annotation: Subtype: Link Rect: 289, 508, 327, 519 Annotation: Subtype: Link Rect: 234, 482, 271, 493 Annotation: Subtype: Link Rect: 149, 457, 187, 467 Annotation: Subtype: Link Rect: 212, 430, 249, 441 Annotation: Subtype: Link Rect: 191, 404, 229, 415 Annotation: Subtype: Link Rect: 149, 379, 187, 390 Annotation: Subtype: Link Rect: 193, 379, 229, 390 Annotation: Subtype: Link Rect: 149, 341, 187, 351 Annotation: Subtype: Link Rect: 430, 314, 467, 325 Annotation: Subtype: Link Rect: 392, 185, 430, 196 Annotation: Subtype: Link Rect: 136, 147, 173, 157 Page: Sequence: 15 Annotations: Annotation: Subtype: Link Rect: 166, 521, 309, 532 Annotation: Subtype: Link Rect: 223, 496, 261, 506 Annotation: Subtype: Link Rect: 100, 366, 137, 377 Annotation: Subtype: Link Rect: 260, 275, 297, 286 Annotation: Subtype: Link Rect: 476, 211, 514, 222 Annotation: Subtype: Link Rect: 76, 139, 166, 170 Annotation: Subtype: Link Rect: 234, 133, 424, 144 Checksum: 05c70c62 Type: CRC32 Checksum: 916a8bd8360f69730d5f1e2b2fa5aee8 Type: MD5 Checksum: 242b0b85ab8d7fda3d52e0ebbb67fc837e623339 Type: SHA-1 Checksum: 127014f75fb0df7cf73efb358a6112e60cc8e433c939d92aeaa87f196e3f9a35 Type: SHA-256