diff --git a/sklearn/metrics/classification.py b/sklearn/metrics/classification.py
index e5ab5b49fcefbfcf334eaa3519f00c441f8c1f1c..09aa4d87b8e21079696b8417d850c9a2868678c3 100644
--- a/sklearn/metrics/classification.py
+++ b/sklearn/metrics/classification.py
@@ -77,8 +77,8 @@ def _check_targets(y_true, y_pred):
         y_type = set(["multiclass"])
 
     if len(y_type) > 1:
-        raise ValueError("Can't handle mix of {0} and {1}"
-                         "".format(type_true, type_pred))
+        raise ValueError("Classification metrics can't handle a mix of {0} "
+                         "and {1} targets".format(type_true, type_pred))
 
     # We can't have more than one value on y_type => The set is no more needed
     y_type = y_type.pop()
diff --git a/sklearn/metrics/tests/test_classification.py b/sklearn/metrics/tests/test_classification.py
index e2acf1de592ad43e3f0c80738cf5e9350f7c88cc..4d6b87f701ea442e4e5412b34494cef63af236e3 100644
--- a/sklearn/metrics/tests/test_classification.py
+++ b/sklearn/metrics/tests/test_classification.py
@@ -1344,7 +1344,8 @@ def test__check_targets():
             if type1 != type2:
                 assert_raise_message(
                     ValueError,
-                    "Can't handle mix of {0} and {1}".format(type1, type2),
+                    "Classification metrics can't handle a mix of {0} and {1} "
+                    "targets".format(type1, type2),
                     _check_targets, y1, y2)
 
             else:
diff --git a/sklearn/metrics/tests/test_common.py b/sklearn/metrics/tests/test_common.py
index d0b855d278e95c117e459afbe968e27886c4a186..5f775aaf9ac8f5e6cd5843eff7b6d7ec80e6a0c1 100644
--- a/sklearn/metrics/tests/test_common.py
+++ b/sklearn/metrics/tests/test_common.py
@@ -636,7 +636,8 @@ def test_inf_nan_input():
     for metric in CLASSIFICATION_METRICS.values():
         for y_true, y_score in invalids:
             assert_raise_message(ValueError,
-                                 "Can't handle mix of binary and continuous",
+                                 "Classification metrics can't handle a mix "
+                                 "of binary and continuous targets",
                                  metric, y_true, y_score)